The DOI matches its Crossref record; 496 of the 496 references it cites were found in a registry or an index; 110 of the 234 sources its claims cite were checked for support.
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
Open accessAbstract
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content. This phenomenon raises significant concerns over the reliability of LLMs in real-world information retrieval (IR) systems and has attracted intensive research to detect and mitigate such hallucinations. Given the open-ended general-purpose attributes inherent to LLMs, LLM hallucinations present distinct challenges that diverge from prior task-specific models. This divergence highlights the urgency for a nuanced understanding and comprehensive overview of recent advances in LLM hallucinations. In this survey, we begin with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, we present a thorough overview of hallucination detection methods and benchmarks. Our discussion then transfers to representative methodologies for mitigating LLM hallucinations. Additionally, we delve into the current limitations faced by retrieval-augmented LLMs in combating hallucinations, offering insights for developing more robust IR systems. Finally, we highlight the promising research directions on LLM hallucinations, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.
Overview
CoChat Summary
TL;DR
This survey proposes a taxonomy of LLM hallucination into factuality and faithfulness, then reviews causes, detection methods, benchmarks, mitigation strategies, and RAG-specific challenges. It also outlines open directions including hallucinations in large vision-language models and understanding knowledge boundaries in LLMs.
Key findings
- Redefines LLM hallucination as factuality hallucination (factual contradiction: entity-error, relation-error; factual fabrication: unverifiability, overclaim) and faithfulness hallucination (instruction inconsistency, context inconsistency, logical inconsistency).
- Identifies causes across data (misinformation/biases, knowledge boundary, inferior alignment data), training (pre-training, SFT, RLHF), and inference (imperfect decoding, over-confidence, softmax bottleneck, reasoning failure).
- Reviews detection and benchmarks: factuality detection via fact-checking and uncertainty estimation; faithfulness detection via fact-based, classifier-based, QA-based, uncertainty-based, and LLM-based metrics. Reported benchmark sizes include TruthfulQA (817 questions), HaluEval (30,000 task-specific and 5,000 general samples), FreshQA (600 hand-crafted questions), and HaluEval 2.0 (8,770 questions across five domains).
- Mitigation is organized by cause: data filtering, model editing, RAG; pre-training/alignment fixes; and factuality/faithfulness enhanced decoding. RAG still faces retrieval failure and generation bottleneck.
Methods
- Design: a survey/overview that proposes a taxonomy and organizes literature on LLM hallucination principles, causes, detection, benchmarks, mitigation, RAG challenges, and future directions.
- Data or sample: no primary dataset or new experiments; synthesizes existing research and benchmarks such as TruthfulQA, HaluEval, FreshQA, and HaluEval 2.0.
- Main analysis: conceptual categorization and qualitative synthesis; no quantitative meta-analysis is reported.
Limitations
- The paper does not explicitly state limitations of the survey itself.
- It states limitations of reviewed methods: RAG can be impacted by irrelevant retrievals and shallow retriever-generator interactions; fact-checking solely via LLM parametric knowledge may yield inaccurate assessments; classifier-based faithfulness metrics are constrained by scarcity of annotated data.
- Text makes evident: as a survey, it presents no original empirical validation or new benchmark results.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
76 Valid · 5 Not valid · 48 Not checked · 108 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Recent studies have highlighted a strong correlation between the model's accuracy on general domain questions and the volume of relevant documents [145] or entity popularity [204] within the pre-training corpora.”
What the sources say
- Supportedcites [145] [145] Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, and Colin Raffel. 2023. Large Language Models Struggle to Learn Long-Tail Knowledge. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202) , Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 15696-15707. https: //proceedings.mlr.press/v202/kandpal23a.html - source
The citation to this paper is attached to the volume of relevant documents, not the separate entity-popularity claim. Section 3.1 (p. 5) reports a strong correlation between question-answering accuracy and relevant pre-training document count across the tested models. (LLM, conf=0.94)
- Partly supportedcites [204] [204] Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023 , Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Computational Linguistics, 9802-9822. https://doi.org/10.18653/v1/2023.acl-long.546 - sourceExperimental — accuracy not yet measured
The “Subject entity popularity predicts memorization” section reports a positive correlation between entity popularity and question-answering accuracy for almost all relationship types. However, the paper measures popularity using Wikipedia page views as a proxy, not entity frequency within pre-training corpora. Its Limitations section also says the experiments rely on synthetic datasets and that applicability to naturally occurring questions is not firmly established. (LLM, conf=0.87)
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Such biases can be inadvertently acquired from internet-based texts, which are rife with diverse and biased viewpoints, and subsequently be propagated into the generated content [155].”
What the sources say
- Partly supportedcites [155] [155] Faisal Ladhak, Esin Durmus, Mirac Suzgun, Tianyi Zhang, Dan Jurafsky, Kathleen McKeown, and Tatsunori Hashimoto. 2023. When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics . Association for Computational Linguistics, Dubrovnik, Croatia, 3206-3219. https://aclanthology.org/2023.eacl-main.234 - sourceExperimental — accuracy not yet measured
The Abstract and §6 Discussion report that pre-training biases can propagate into generated summaries as hallucinated facts. But §6 leaves the source of those biases for future work and treats stereotyping in pre-training data as one possibility; it does not establish that they were acquired from internet-based texts. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Neural networks possess an intrinsic tendency to memorize training data [35]”
What the sources say
- Partly supportedcites [35] [35] Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21) . 2633-2650. - sourceExperimental — accuracy not yet measured
Section 3.1 (p. 3) says memorization is in many ways an essential component of language models, and the Introduction (p. 1) demonstrates that large language models memorize individual training examples. The claim extends that finding to neural networks generally; the cited passages do not establish an intrinsic tendency across all neural networks. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, certain biases are intrinsically tied to hallucinations, especially those related to gender [242] and nationality [155, 226].”
What the sources say
- Not matchedcites [242]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [155] [155] Faisal Ladhak, Esin Durmus, Mirac Suzgun, Tianyi Zhang, Dan Jurafsky, Kathleen McKeown, and Tatsunori Hashimoto. 2023. When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics . Association for Computational Linguistics, Dubrovnik, Croatia, 3206-3219. https://aclanthology.org/2023.eacl-main.234 - source
The Introduction and Section 3.3 report a strong association between pre-trained models’ name–nationality bias and nationality hallucinations in downstream text summarization. The citation to this paper is attached to nationality; the separate gender citation is not assessed here. (LLM, conf=0.89)
- Not matchedcites [226]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
Every source the paper cites for this claim was checked and supports it.
In the paper
“this memorization tendency grows with model size [34, 54]”
What the sources say
- Supportedcites [34] [34] Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. 2022. Quantifying memorization across neural language models. ArXiv preprint abs/2202.07646 (2022). https://arxiv.org/ abs/2202.07646 - source
Section 4.1 (p. 4) reports that larger models memorize significantly more than smaller models. The Introduction (p. 2) specifies that this finding is within model families, and the Conclusion (p. 9) describes memorization as scaling with model size. (LLM, conf=0.94)
- Supportedcites [54] [54] Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, H source
Section 7, “Memorization” (p. 35), explicitly concludes that larger models have a higher memorization rate than smaller models. It also reports that the exact-continuation match rate rises from 1.6% for the 8B model to 2.4% for the 540B model. (LLM, conf=0.94)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
102 more claims · 41 with their cited sources checked
Create a free account to see all 237 claims and to verify the 13 references still open.
- Probably not a substantial claim. 97
- It may state two separate claims as one. 55
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, LLMs exhibit hallucination and fabrication errors that are unacceptable for quantitative modeling [19, 20, 21].”
From Structured Schemas for Provenance‐Rich, LLM ‐Assisted QSP Model Calibration (2026) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In particular, the generation of non-existent academic references or legal precedents has been widely recognized as a critical issue [4].”
From Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy (2025) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Retrieval augmentation, tool use, citation systems, constrained decoding, domain-specific training, and multimodal grounding can all supply partial external anchoring, and they alter both the frequency and the detectability of unsupported claims [15,29].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [15]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These measures do reduce the frequency of unsupported claims and improve the odds that a learner can detect one, and the argument here does not depend on denying it [15,29].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [15]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents.It does not check whether retrieved evidence is attributed to the correct entity.”
From Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation (2026) · cites this paper as Huang et al., 2025
Experimental — accuracy not yet measured
21 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2.3 Hallucinations in Large Language Models · p. 7
“the final answer of x=4 is inconsistent with the reasoning chain, leading to an incorrect result.”
§ 2.3 Hallucinations in Large Language Models · p. 6
“Step 2: Divide both sides by 2 to get: x = 3. So the result of the equation is x=3.”
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 1×
“To align with human preferences, RLHF optimizes the LLM to generate outputs that maximize the reward provided by the trained preference model, typically employing a reinforcement learning algorithm, such as Proximal Policy Optimization (PPO)(Schulman et al., 2017).”
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“While scaling up pre-training data substantially enhances the competencies of LLMs (Kaplan et al., 2020; Hoffmann et al., 2022), challenges arise in maintaining consistent data quality, which can potentially introduce misinformation and biases (Bender et al., 2021; Weidinger et al., 2021).”
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · cited 10×
“By retrieving evidence from external knowledge bases, RAG enables LLMs to be equipped with up-to-date knowledge and generate responses conditioning on relevant evidence.”
InfluentialLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(2017) · doi:10.1109/cvpr35066.2017 · Cited by 7,141
Research works printed but not linked: 33
- ArXiv. 2023. arxiv dataset. Retrieved from https://www.kaggle.com/datasets/Cornell-University/arxiv/versions/134
- Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled sampling for sequence prediction with recurrent neural networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems. Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.), 1171–1179. Retrieved from https://proceedings.neurips.cc/paper/2015/hash/e995f98d56967d946471af29d7bf99f1-Abstract.html
- Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from trillions of tokens. In Proceedings of theInternational Conference on Machine Learning (ICML ’22). Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato (Eds.), Proceedings of Machine Learning Research, Vol. 162, PMLR, 2206–2240. Retrieved from https://proceedings.mlr.press/v162/borgeaud22a.html
- 10.5555/3495724.3495883 · doi:10.5555/3495724.3495883
- 10.5555/3600270.3602050 · doi:10.5555/3600270.3602050
- Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. In Proceedings of the 31st International Conference on Neural Information Processing Systems. Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.), 4299–4307. Retrieved from https://proceedings.neurips.cc/paper/2017/hash/d5e2c0adad503c91f91df240d0cd4e49-Abstract.html
- Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and play language models: A simple approach to controlled text generation. In Proceedings of the 8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=H1edEyBKDS
- Bikash Gyawali, Lucas Anastasiou, and Petr Knoth. 2020. Deduplication of scholarly documents using locality sensitive hashing and word embeddings. In Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association, 901–910. Retrieved from https://aclanthology.org/2020.lrec-1.113
- Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The curious case of neural text degeneration. In Proceedings of the 8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=rygGQyrFvH
- Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie Zhou, Wenge Rong, and Zhang Xiong. 2023d. Transformer-Patcher: One mistake worth one neuron. In Proceedings of the 11th International Conference on Learning Representations (ICLR ’23). OpenReview.net. Retrieved from https://openreview.net/pdf?id=4oYUGeGBPm
- Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2022. Unsupervised dense information retrieval with contrastive learning. Transactions on Machine Learning Research 2022 (2022). Retrieved from https://openreview.net/forum?id=jKN1pXi7b0
- Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, and Colin Raffel. 2023. Large language models struggle to learn long-tail knowledge. In Proceedings of the International Conference on Machine Learning (ICML ’23). Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.), Proceedings of Machine Learning Research, Vol. 202, PMLR, 15696–15707. Retrieved from https://proceedings.mlr.press/v202/kandpal23a.html
- Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2020. Generalization through memorization: Nearest neighbor language models. In Proceedings of the 8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=HklBjCEKvH
- 10.5555/3600270.3601883 · doi:10.5555/3600270.3601883
- Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proceedings of the 31st International Conference on Neural Information Processing Systems. Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.), 6402–6413. Retrieved from https://proceedings.neurips.cc/paper/2017/hash/9ef2ed4b7fd2c810847ffa5fa85bce38-Abstract.html
- 10.5555/3600270.3602776 · doi:10.5555/3600270.3602776
- 10.5555/3495724.3496517 · doi:10.5555/3495724.3496517
- Jinming Li, Wentao Zhang, Tian Wang, Guanglei Xiong, Alan Lu, and Gerard Medioni. 2023. GPT4Rec: A generative framework for personalized recommendation and user interests interpretation. In Proceedings of the SIGIR Workshop on eCommerce Co-located with the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 23). Surya Kallumadi, Yubin Kim, Tracy Holloway King, Shervin Malmasi, Maarten de Rijke, and Jacopo Tagliabue (Eds.), CEUR Workshop Proceedings, Vol. 3589, CEUR-WS.org. Retrieved from https://ceur-ws.org/Vol-3589/paper_2.pdf
- Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out. Association for Computational Linguistics, 74–81. Retrieved from https://aclanthology.org/W04-1013
- 10.5555/3600270.3601532 · doi:10.5555/3600270.3601532
- Kevin Meng, Arnab Sen Sharma, Alex J. Andonian, Yonatan Belinkov, and David Bau. 2023. Mass-editing memory in a transformer. In Proceedings of the 11th International Conference on Learning Representations (ICLR ’23). OpenReview.net. Retrieved from https://openreview.net/pdf?id=MkbcAHIYgyS
- Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D. Manning. 2022. Fast model editing at scale. In Proceedings of the 10th International Conference on Learning Representations (ICLR ’22). OpenReview.net. Retrieved from https://openreview.net/forum?id=0DcZxeWfOPt
- Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. In NeurIPS. Retrieved from http://papers.nips.cc/paper_files/paper/2022/hash/b1efde53be364a73914f58805a001731-Abstract-Conference.html
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.
- Anton Sinitsin, Vsevolod Plokhotnyuk, Dmitriy Pyrkin, Sergei Popov, and Artem Babenko. 2020. Editable neural networks. In Proceedings of the8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=HJedXaEtvS
- 10.5555/3495724.3495977 · doi:10.5555/3495724.3495977
- Chenmien Tan, Ge Zhang, and Jie Fu. 2024. Massive editing for large language model via meta learning. In Proceedings of the 12th International Conference on Learning Representations. Retrieved from https://openreview.net/forum?id=L6L1CJQ2PE
- Zirui Wang Jiahui Yu Adams Wei Yu Zihang Dai Yulia Tsvetkov and Yuan Cao. 2022. SimVLM: Simple visual language model pretraining with weak supervision. In Proceedings of the 10th International Conference on Learning Representations (ICLR ’22). OpenReview.net. Retrieved from https://openreview.net/forum?id=GUrhfTuf_3
- 10.5555/3600270.3602070 · doi:10.5555/3600270.3602070
- Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov, and William W. Cohen. 2018. Breaking the softmax bottleneck: A high-rank RNN language model. In Proceedings of the6th International Conference on Learning Representations (ICLR ’18). OpenReview.net. Retrieved from https://openreview.net/forum?id=HkwZSG-CZ
- Zhilin Yang, Thang Luong, Ruslan Salakhutdinov, and Quoc V. Le. 2019. Mixtape: Breaking the softmax bottleneck efficiently. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS ’19). Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett (Eds.), 15922–15930. Retrieved from https://proceedings.neurips.cc/paper/2019/hash/512fc3c5227f637e41437c999a2d3169-Abstract.html
- Weizhe Yuan, Graham Neubig, and Pengfei Liu. 2021. BARTScore: Evaluating generated text as text generation. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS ’21). Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.), 27263–27277. Retrieved from https://proceedings.neurips.cc/paper/2021/hash/e4d2b6e6fdeca3e60e0f1a62fee3d9dd-Abstract.html
- Hugh Zhang, Daniel Duckworth, Daphne Ippolito, and Arvind Neelakantan. 2021. Trading off diversity and quality in natural language generation. In Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval). Association for Computational Linguistics, 25–33. Retrieved from https://aclanthology.org/2021.humeval-1.3
Cited by
Items 801–900 of 2,241
LLM Assisted Dual-View Awareness Framework for Smart Contract Vulnerability Detection
Wang, J., Yue, Y., Hu, D., Li, Q., Li, J., & Zhu, W. (2025) · 2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre66568.2025.00022 · Cited by 1
“However, due to their intrinsic characteristics as lexical probabilistic models, LLMs lack the capacity for formal syntactic analysis and exhibit high false positive rate, which require further validation in later stages [24, 25].”
Hè, H., & Apostolaki, M. (2025) · ACM Workshop on Hot Topics in Networks (HotNets) · doi:10.1145/3772356.3772406 · Cited by 4
Duan, J., Xue, W., Kang, Z., Liu, S., & Xia, J. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3633870 · Cited by 4
“Since users often select multiple phrases for single class, the encoded vectors are averaged to initialize the continuous text vector representation, thereby capturing the comprehensive semantic attributes of the target class.”
MRAN-VQA: Multimodal Recursive Attention Network for Visual Question Answering
Islam, M. S., Rony, M. A. T., Sarker, M. M. H., Bhuiyan, M. K. B., Saib, M., Aktarujjaman, M., Uddin, M. S., Algarni, A. D., Azar, A. T., & El‐Shafai, W. (2025) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2025.102232 · Cited by 2
L3M+P: Lifelong Planning with Large Language Models
Agarwal, K., Jiang, Y., Hu, J., Liu, B., & Stone, P. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247529 · Cited by 7
“However, the report can grow arbitrarily long, so this approach is prone to model hallucination, which can significantly affect the accuracy of the agent [9].”
Lightweight Self-Consistency Voting Framework for Reliable Hallucination Detection in LLMs
Padmavathi, A., Pandit, B., & Khaitan, G. (2025) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito66076.2025.11241896 · Cited by 1
“…challenge has matured from a specialized research question to a significant bottleneck for reliable NLP. Early mapping surveys like Huang et al. [12] and Ji et al. [13] methodically charted the topography, dividing hallucinations into intrinsic and extrinsic, and noting such types as factual…”
Multilingual QA-RAG: Evaluating LLMs' Contradiction Handling in English and Kazakh
Tleubayeva, A., Mansurova, A., Aubakirov, S., Tabuldin, A., Shomanov, A., & Makhambetova, Z. (2025) · ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD) · doi:10.1109/snpd65828.2025.11254178 · Cited by 1
“However, along with their advantages, LLMs also carry serious risks, the main of which is the tendency to generate implausible or factually incorrect information, which is commonly referred to as "hallucinations" [3].”
Chadimová, M., Jurášek, E., & Kliegr, T. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104493 · Cited by 2
Identifying and Addressing User-level Security Concerns in Smart Homes Using “Smaller” LLMs
Chowdhury, H. H., Anonto, R. A., Jajodia, S., et al. (2025) · International Conference on Privacy, Security and Trust (PST) · doi:10.1109/pst65910.2025.11268837 · Cited by 1
“Without domain-specific fine-tuning, they often yield incorrect or incomplete answers [12], lacking the specialized knowledge needed for this nuanced domain.”
CM-MRAG: A multimodal retrieval-augmented framework for content moderation
Qu, W., Chen, C., Lu, W., Wei, Y., & Li, T. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130768 · Cited by 2
Brünnhäußer, J., Zhang, X., Konietzko, E. P., & Kehl, S. (2025) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme64568.2025.11277979 · Cited by 2
A Hybrid Neuro-Symbolic Reasoning Framework for Automated Factual Verification in Conversational AI
Chin, W. H., Guo, Y., Loo, C. K., & Kubota, N. (2025) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc66258.2025.11280070 · Cited by 18
“Despite these advances, LLMs continue to struggle with factual consistency, often generating plausible-sounding but incorrect information, a phenomenon broadly termed ”hallucination” [4, 5, 6].”
A Brief History of Formal Methods in China
Zhan, N., Woodcock, J., Wang, J., & Chen, M. (2025) · Formal Aspects of Computing · doi:10.1145/3783996 · Cited by 1
Structured Multimodal RAG: Document-Aware Retrieval and Alignment for Hallucination Mitigation
Meng, J. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290404 · Cited by 1
“Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language processing (NLP) tasks such as question answering, summarization, and machine translation [1].”
An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG
Grekhova, A., Palchunov, D. E., Shishkin, A., & Zaitsev, A. (2025) · International Scientific-Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE) · doi:10.1109/apeie66761.2025.11289384 · Cited by 1
“Firstly, LLMs are prone to “hallucinations”, i.e. generating information that is not based on real data, which can lead to false or contradictory statements [2].”
Detection of Hallucinations Based on the Internal States of Large Language Models
Aisin, T. R., & Shamardina, T. V. (2025) · Automatic Documentation and Mathematical Linguistics · doi:10.26907/1562-5419-2025-28-6-1282-1305 · Cited by 4
A bibliometric analysis of large language models in China
Lao, B., Zhi, S. Z., & Lü, W. (2025) · Online Information Review · doi:10.1108/oir-01-2025-0049 · Cited by 1
ViseGPT: Towards Better Alignment of LLM-generated Data Wrangling Scripts and User Prompts
Zhu, J., Cheng, X., Luo, Z., Zhou, Y., Shu, X., Weng, D., & Wu, Y. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747689 · Cited by 5
Kou, J., Lu, X., Yin, A., Zhang, W., Fang, X., Li, Y., Pan, T., Zhang, L., Cheng, G., Yuan, H., et al. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189154 · Cited by 7
Son, D., Kim, G., Oh, H., & Sundar, S. S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113447 · Cited by 1
Using large language model to aid in teaching medical imaging report writing
Chen, Y., Xiang, P., Zhou, Q., Li, C., Zhang, X., Wang, J., Wang, H. J., Gao, Z., Yang, Z., Ye, S., et al. (2025) · Medical Teacher · doi:10.1080/0142159x.2025.2603353 · Cited by 2
Self-citationLarge AI Models Have a Prioritization Problem: Policy Implications and Solutions
Jackson, J. C., Liu, Y.-Z., Wang, Z., & Brady, W. J. (2025) · Policy Insights from the Behavioral and Brain Sciences · doi:10.1177/23727322251408311 · Cited by 3
“Hallucination is an especially common problem in domains where knowledge is rapidly evolving (e.g., recent political events), copyright restricted (e.g., new novels or paywalled research), or infrequently discussed (e.g., rare diseases) (Huang et al., 2025).”
Hazrati, P., Zibandehkhooy, T., Sabri, H., Romandini, M., & Barootchi, S. (2025) · Journal of Periodontal Research · doi:10.1111/jre.70071 · Cited by 3
Zhao, X., Jin, Y., Wang, Y. S., & Zhang, M. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104574 · Cited by 1
Research on a Dual‐Mode Human–Robot Interaction Method Based on a Large Language Model
Guo, J., & Han, X. (2026) · IET Cyber-Systems and Robotics · doi:10.1049/csy2.70037 · Cited by 2
Revisiting data analysis with Pre-trained foundation models
Liang, C., Yang, D., Liang, Z., Liang, Z., Zhang, T., Xiao, B., Yang, Y., Wang, W., & Wang, H. (2026) · The VLDB Journal · doi:10.1007/s00778-025-00953-5 · Cited by 5
Self-citationDai, Y., Zhang, H., Wang, J., & Liao, J. (2026) · Computer Communications · doi:10.1016/j.comcom.2026.108428 · Cited by 2
SafeRAG: Secure Cloud-Based Retrieval-Augmented Generation for LLM-Empowered Voice Assistants
Chang, Y., Luan, T. H., Wang, S., & Wang, Y. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3654070 · Cited by 2
“Neverthe-less, LLM-driven assistants still suffer from hallucination [7], [8], generating responses that are grammatically correct but factually inaccurate or unsupported, which significantly reduces their reliability.”
Guo, Q. J., Li, X., Chen, J., et al. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11323137 · Cited by 1
“Additionally, the occurrence of hallucinations of LLMs may lead to inaccurate decisions [11], thereby undermining reliability.”
Relative Performance Bandits: An Adaptive RAG Framework with Reward-Aware Exploration
Dai, Y., Li, J., & Li, B. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11322957 · Cited by 1
“Large language models (LLMs) have exhibited remarkable reasoning capabilities, leading to their widespread adoption in daily tasks [1], but their reliance on parameterized knowledge often results in hallucinations due to limitations in accuracy, coverage, and timeliness [2], [3].”
Liao, W., Li, M., Ma, C., Han, Y., Wang, D., Liu, H., Wang, Y., Feng, Z., Wang, H., & Guan, Y. (2026) · Journal of Medical Internet Research · doi:10.2196/83188 · Cited by 3
“However, indicators related to safety risks, such as bias and hallucinations, received limited attention [26,27].”
Self-citationG²SQL: guided & guarded Text-to-SQL generation with two-stage verification
Li, X., You, J., Li, H., Peng, J., Chen, X., Guo, Z., Li, K., & Xu, T. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131276 · Cited by 3
Medication Counseling with Large Language Models: Balancing Flexibility and Rigidity
Sabel, J., Wingren, M., Lundell, A., Andersson, S., Rosenberg, S., Hägglund, S., Estman, L. S., & Andtfolk, M. (2025) · IEEE International Conference on Agents (ICA) · doi:10.1109/ica67499.2025.00047 · Cited by 1
“The greater the contextual information, the more likely the model is to hallucinate, for example by being overly confident or simply disregarding relevant facts of a given situation [8].”
Xu, X., & Wu, J. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3655508 · Cited by 9
“With the significant impact of hallucinations, researchers have made numerous investigations and studies [10] on how to mitigate this problem.”
InfluentialDegiovanni, R., & Cabot, J. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00313 · Cited by 1
“Although promising, LLMs are prone to hallucinations [10] and biases [7], which constitutes a big risk for companies aiming to integrate LLMs into their educational products.”
Chen, J., Tian, J., Xu, W., Xia, W., & Zhou, L. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356911 · Cited by 2
“Crucially, their performance degrades with more accessible, open-source LLMs, whose smaller scale curtails reasoning capabilities and renders them susceptible to ”hallucination” [22]—an unacceptable risk when dealing with patient safety or clinical data.”
He, J., Jia, M., Jia, Z., Duan, J., Song, Y., & Wang, J. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11357045 · Cited by 9
“However, their adoption faces challenges such as hallucination [4], [5] and the resource-intensive nature of knowledge updates [6].”
Evaluating LLM-Based Detection of Malicious Package Updates in npm
Wyss, E., Tassio, D., Carli, L. D., & Davidson, D. (2025) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1109/raid67961.2025.00047 · Cited by 5
“Moreover, LLMs are shown to potentially hallucinate false information in practice [55] and are prone to reinforcing biases present in their own training data [56].”
Equipping a Virtual Reading Promoter for Digital Libraries with Retrieval-Augmented Generation
Li, Z. (2025) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1109/jcdl67857.2025.00054 · Cited by 3
“Recent intelligent systems based on LLMs are prone to generating hallucinations [4].”
Chang, Y., Wang, S., Luan, T. H., Wang, Y., & Su, Z. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00122 · Cited by 1
“However, despite their impressive capabilities, LLMs often suffer from the problem of hallucination [7], [8], where generated responses appear fluent but are factually incorrect or ungrounded.”
Peng, J., Zhuang, X., Chen, Y., Xu, H., Du, Y., Zhu, B., Zhao, G., Wang, Y., Ling, Y., & Zhang, G. (2026) · Biosafety and Health · doi:10.1016/j.bsheal.2026.02.001 · Cited by 2
PlasRAG: comprehensive plasmid characterization and retrieval through sequence-text alignment
Ji, Y., Liao, H., Guan, J., Shang, J., & Sun, Y. (2026) · Genome biology · doi:10.1186/s13059-026-03966-7 · Cited by 1
Sanyal, P., Rathore, K., & Arjunan, R. V. (2026) · Scientific Reports · doi:10.1038/s41598-026-38913-w · Cited by 3
“This improves retrieval accuracy and ensures that the retrieved passages align better with the user’s intent, ultimately enhancing factuality and reducing hallucinations in the generated output 19 .”
Subahi, A. F. (2026) · IEEE Access · doi:10.1109/access.2026.3663331 · Cited by 1
“This approach minimizes the risk of hallucinations by ‘‘locking in’’ a template that has been verified for structural correctness [35].”
Processing unstructured clinical notes with LLMs: applying the CMQOE framework for hypertension
Gong, A., Fan, B., Liu, Y., Wang, D., Tong, Z., Wei, X., Jia, A., Zhang, Z., & Wu, S. (2026) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-026-03527-x · Cited by 1
Burns, D. T., Bice, C., Johnson, P. E., Chia, N., & Robinson, T. (2026) · Journal of Medical Internet Research · doi:10.2196/85516 · Cited by 2
“This problem is further compounded by chatbots’ tendency to provide responses in a manner that conveys strong certainty and expertise in the content [64,65].”
Song, Z., Kong, X., Bao, X., Zhou, Y., Jiao, J., Liu, S., Zhou, Y., & Qi, H. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131627 · Cited by 8
“This issue poses a significant barrier in knowledge-intensive applications, such as medical diagnosis, where factual accuracy is paramount (Ji et al., 2023; Huang et al., 2025; Luo et al., 2026; Płonka et al., 2025; Chi et al., 2026; L. Li et al., 2025).”
Wang, Z., Li, L., Chen, L., Xu, X., Li, M., & Su, Y. (2025) · International Conference on Wireless Communication, Networking and Internet of Things (WCNIoT) · doi:10.1109/wcniot67424.2025.11381315 · Cited by 1
“It stems from data distribution bias, generation uncertainty, and imperfect instruction alignment, and is regarded as an unavoidable phenomenon in large generative models [20].”
Augmenting Small Language Model for Better Medical Question Answering through Source Authentication
Das, S., Chatterji, S., & Mukherjee, I. (2026) · ACM Transactions on Information Systems · doi:10.1145/3797887 · Cited by 3
JANUS: A Difference-Oriented Analyzer for Financial Centralized Risks in Smart Contracts
Wang, W., Zhang, P. F., Ji, R., Huang, W., Meng, Z., Cui, J., Zhong, H., & Xiong, Y. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3664823 · Cited by 1
“(cid:2) The results are more reliable: LLMs suffer from ”hallu-cination,” which may lead to incorrect judgments [52].”
Hallucination-Free Automatic Question & Answer Generation for Intuitive Learning
Wang, N., & Katsaggelos, A. K. (2025) · IEEE International Conference on Image Processing Workshops (ICIPW) · doi:10.1109/icipw68931.2025.11386040 · Cited by 3
“Despite these advancements, one fundamental challenge remains: hallucinations [16-18], instances where the AI produces incorrect, misleading, or logically inconsistent outputs.”
An AI-Driven Ensemble Framework for Personalized Career Coaching and Job Readiness
Naik, C., Gadad, T. R., Varshitha, R., B, K. Y., & N, B. S. (2025) · International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications (COSMIC) · doi:10.1109/cosmic67569.2025.11380995 · Cited by 1
Enhanced Web Testing with LLMs: A Research Roadmap
Wang, W., Guo, Z., Yan, Q., Yang, Z., Zhang, Y., Xu, G., Li, X., & Wu, B. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3795887 · Cited by 5
Calibrated Trust in Dealing with LLM Hallucinations: A Qualitative Study
Ryser, A., Allwein, F., & Schlippe, T. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391250 · Cited by 7
“This highlights the need to better understand user behavior and verification strategies in response to hallucinations [22].”
InfluentialWhere Risk Travels: A Dual‐Path Model of Media and Governance in the Perception of AI Hallucination
Yao, X., & Xi, Y. (2026) · Policy & Internet · doi:10.1002/poi3.70032 · Cited by 1
Zheng, Y., Zhang, X., Du, K., Li, J., Li, L., Liu, S., Li, T., & Jin, Z. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114212 · Cited by 2
Language Modeling and Large Language Models
Yu, J. S., & Yao, Y. (2026) · Springer eBooks · doi:10.1007/978-981-95-4632-9_2 · Cited by 1
Kriz, A., Janes, E. L., Shen, X., & Arbel, T. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00142 · Cited by 10
“Second, it is well-established that LLMs hallucinate, propagate bias, and produce harmful content [8, 10], often while presenting their inaccurate outputs as fact.”
A Multi-Year Survey of Use and Perceptions of Generative AI in Higher Education
Crescenzi, A., Choi, B., Huang, P.-P., Gautier, E., Little, R., & Pandya, S. (2026) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3786304.3787867 · Cited by 3
“This may also reflect academic skepticism toward gen AI technology as hallucination persists [29].”
Huang, S. L., & Cheng, J. (2025) · International Conference on Communication Technology and Information Technology (ICCTIT) · doi:10.1109/icctit68197.2025.11406504 · Cited by 1
“Large Language Models (LLMs) have revolutionized NLP but face two critical hurdles: Knowledge Cutoff and Halluci-nation [1].”
UAV-Based Jamming Detection for Large Language Model-Enabled Wireless Networks
Chen, Q., Xiao, L., Wang, P., et al. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3669447 · Cited by 1
“links that carry prompts and multimodal inputs remain vulnerable to jamming, which can corrupt critical tokens or images and induce inference failures or hallucinations [3].”
Self-citationUniEval-RAG: A Unified End-to-End Evaluation Framework for RAG Systems
Liang, S., Gong, X., Li, F., Zhou, H., Wu, Y., & Liao, C. (2025) · International Conference on Computer, Internet of Things and Smart City (CIoTSC) · doi:10.1109/ciotsc67482.2025.11412981 · Cited by 1
“This integration has been shown to help mitigate the hallucination problem commonly observed in LLMs [6]–[8].”
Revisiting the role of linguistic knowledge in large language models through prompting
Sataer, Y., Gao, M., Shi, C., Li, B., & Gao, Z. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115667 · Cited by 1
Innovation under censorship: Effects on cultural production in early modern England
Grajzl, P., & Murrell, P. (2026) · Journal of Comparative Economics · doi:10.1016/j.jce.2026.02.004 · Cited by 4
Wu, J., Luo, M., Ye, Q., & Ye, D. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07095-3 · Cited by 1
“5, LLaMA) to directly generate entities and their categories through a sequence-to-sequence framework [6].”
Bao, R., Chen, J., Huang, Y., Liang, S., & Cheng, L. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2026.2634138 · Cited by 1
“The risk of “hallucinations” (Huang et al., 2025) poses a significant threat to educational integrity.”
Push and Pull : Defending against Retrieval Poisoning Attacks via Embedding Space Reshaping
He, L., Zhang, X., Liu, Q., Li, C., Liu, Z., Zhou, P., & Su, S. (2026) · ACM Transactions on Information Systems · doi:10.1145/3800948 · Cited by 5
Zhang, X. (2026) · AI & Future Society · doi:10.63802/afs.v2.i1.208 · Cited by 1
Automated Single-Turn Solution Recommendation System for Software IT Support Tickets
Isaza, P. T., Nidd, M., Zheutlin, N., Ahn, J., Bhatt, C., Deng, Y., Mahindru, R., Franz, M., Florian, H., & Roukos, S. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402036 · Cited by 1
“One way to combat hallucination is by evaluating the groundedness (or faithfulness) of the generated answer within the provided context [13].”
InfluentialFrom Verification Burden to Trusted Collaboration: Design Goals for LLM-Assisted Literature Reviews
Nogueira, B., Geyer, W., Anderson, A. W., Li, T. J.-J., Kim, D., Moniz, N., & Chawla, N. V. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742414.3794723 · Cited by 4
Liu, Y., Zheng, X., Cai, C., Yuan, X., & Wang, C. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3671484 · Cited by 3
“Discussion: Instruction fine-tuning enhances model performance and mitigates hallucination issues by guiding the model with task-specific instructions [45].”
DispatchMAS: fusing taxonomy and artificial intelligence agents for emergency medical services
Li, X., Yu, H., Wang, W., Wu, Y., Zhou, J., Hua, W., Lin, X., Tan, W., Zhu, L., Chen, B., et al. (2026) · BMC Emergency Medicine · doi:10.1186/s12873-026-01540-9 · Cited by 1
“A well-known limitation of LLMs is their tendency to generate plausible but inaccurate or fabricated responses, commonly referred to as hallucinations[31].”
Zhang, Z., Zhang, Y., Zeng, D., Liu, K., & Zhao, J. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3675803 · Cited by 3
“LLMs are prone to generating factually incorrect information, referred to as hallucination, which significantly undermines their reliability and trustworthiness [16], [17].”
Algebraic Semantics for Interpretable Reasoning in Large Language Models
Liu, P., & Li, Y. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123383 · Cited by 2
Zhang, T., Nguyen, V. T., & Shimizu, T. (2026) · Journal of Open Innovation Technology Market and Complexity · doi:10.1016/j.joitmc.2026.100757 · Cited by 1
CALL: Context-Aware Low-Latency Retrieval in Disk-Based Vector Databases
Jeong, Y., Cho, H., Park, K., Kim, Y., & Park, S. (2025) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.1109/hipc66333.2025.00026 · Cited by 7
“Large Language Models (LLMs) often generate responses that include incorrect information, when prompted with queries beyond their training data [1].”
Robust prototype-aware representation refinement for LLM-based sequential recommendation
Ma, J., Qin, J., Chen, Y., Feng, Q., & Liu, S. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113550 · Cited by 2
When Semantic Similarity Fails: Analyzing Metric Divergence in Legal RAG Evaluation
SILVA, E. D. D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_43 · Cited by 1
Domain-Adapted Large Language Model for Mine Safety Question Answering
Yu, H., Li, Y.-Q., & Chen, S.-X. (2025) · 2025 5th International Symposium on Artificial Intelligence and Big Data (AIBDF) · doi:10.1109/aibdf67964.2025.11440776 · Cited by 1
“Such models often lack domain-specific expertise, misuse specialized terminology, or generate unsupported content [4], [6].”
Traditional RAG vs. Agentic RAG: A Comparative Study of Retrieval-Augmented Systems
Neha, F., & Bhati, D. (2025) · IEEE International Conference on Future Machine Learning and Data Science (FMLDS) · doi:10.1109/fmlds67896.2025.00073 · Cited by 7
“However, their reliance on static parametric knowledge leads to factual inaccuracies and hallucinations in knowledge-intensive tasks [1].”
Brunyé, T. T., Petrimoulx, M. V., & Cantelon, J. A. (2026) · Sensors · doi:10.3390/s26072034 · Cited by 3
Shao, Y., Du, Z. Y., Liu, B., Wen, H., Zhang, X., & Zhang, C. (2026) · International Conference on Artificial Intelligence and Social Network Systems (AISNS) · doi:10.1109/aisns67921.2026.11440489 · Cited by 1
“However, LLMs still face challenges such as insufficient knowledge timeliness, frequent hallucination phenomena, and poor adaptability to vertical domains [1-2].”
Generative AI-Driven Cybersecurity Deception: A Brief Survey of Large Language Model Based Honeypots
Singh, V. K. (2025) · International Conference on Electrical, Electronics, Communication and Computers (ELEXCOM) · doi:10.1109/elexcom67950.2025.11451325 · Cited by 2
“LLM hallucinations : LLMs sometimes produce answers that sound plausible, however, factually incorrect (hallucination) [37].”
Metacognition of ChatGPT in confidence judgements
YOSHIZAWA, S., Onzo, A., Nozawa, S., Takano, T., Ishikawa, T., & Mogi, K. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1694192 · Cited by 2
Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding
Hsu, T.-W., Lu, K.-H., Chiang, C.-H., & Lee, H.-Y. (2025) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru65441.2025.11434595 · Cited by 34
“Hallucination, where a model generates content that is not supported by the input or factual knowledge [25], is a critical safety issue for LLMs and large vision language models [26]– [28].”
Shinde, A., Mhaismale, H., Pawar, P., Mane, S., & Bembde, A. (2026) · Drug Development and Industrial Pharmacy · doi:10.1080/03639045.2026.2649846 · Cited by 3
“…decision-making methods are not straightforward, and this decreases the level of trust and acceptance of the methods by the regulatory authorities [72]. on top of that, llMs are able to produce misleading or fake information, which is dangerous in clinical situations [72]. the problem must be…”
InfluentialRaza, F. M., Yang, S. L., Srinivasan, S., & DeFranco, J. F. (2026) · Computer · doi:10.1109/mc.2026.3664470 · Cited by 1
“Hallucinations, which occur at rates of 15%–30% in knowledge-intensive applications, further erode reliability; for example, an LLM used in legal services may fabricate case precedents, potentially leading to compliance violations [9], [10].”
Foundation Models for Autonomous Driving Systems: An Initial Roadmap
Wu, X.-F., Cheng, M.-F., Ren, X.-N., Hu, Q., Chen, J.-L., Huang, Y.-H., Cordy, M., Zhang, Y., Xie, X.-F., Ma, L., et al. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3807455 · Cited by 11
Ask ChatGPT: caveats and mitigations for individual users of AI chatbots
Wang, C., & Kantarcıoğlu, M. (2026) · AI and Ethics · doi:10.1007/s43681-026-01089-0 · Cited by 3
VeritasFi : An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
Tai, Z., Wu, H., Hu, Q., Chi, J., He, H., Ding, L., Kwok, T. S. T., Xiao, B., Hua, Y., Wang, S., et al. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792795 · Cited by 6
Active Retrieval-Augmented Generation with Conflict-Fused Uncertainty Quantification
Tang, T., Yue, X., Chen, Y., Shi, J., & Ding, S. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792926 · Cited by 1
Li, J., Zhu, S., & Xiong, D. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104819 · Cited by 1
A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM
Wang, B., Ma, J., Lin, H., Yang, Z., Yang, R., Tian, Y., & Chang, Y. (2026) · ACM Transactions on Information Systems · doi:10.1145/3810244 · Cited by 4
Guilty apology and trust repair in generative artificial intelligence: the role of mind perception
Xu, F., Yuan, Z., Jin, S., Niu, G., & Zhou, Z. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103813 · Cited by 2
DMAP: Human-Aligned Structural Document Map for Multimodal Document Understanding
Fu, S., Zhang, Y., Xiang, Y., Du, X., & Tang, J. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792229 · Cited by 3
Beyond markets and hierarchies: How GenAI enables unbounded cognitive fusion
Wan, Y. (2026) · Electronic Markets · doi:10.1007/s12525-026-00898-9 · Cited by 5
LLM-Driven Framework for Industrial Design Automation
He, S., Wang, X., Chen, Z., Liao, J., Wang, B., Xu, J., Guan, X., Yu, S., & Li, Y. (2026) · Engineering · doi:10.1016/j.eng.2026.04.009 · Cited by 1
Huang, H., Dai, G., Niu, F., Dong, L., Yin, N., Fan, X., Wang, S., Jing, L., & Zhang, B. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132677 · Cited by 22
Reinhard, P., Li, M. M., Peters, C., & Leimeister, J. M. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10716-4 · Cited by 11
Qinjie, S. (2026) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2026.100601 · Cited by 5
Metadata
- Authors
- Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., & Liu, T.
- Affiliations
- Harbin Institute of Technology (CN)
- Huawei Technologies (China) (CN)
- ORCID
- Venue
- ACM Transactions on Information Systems
- Published
- 2025-01-24
- Volume
- 43
- Issue
- 2
- Pages
- 1-55
- ISSN
- 1046-8188 (ISSN-L)
- 1558-2868
- OpenAlex
- W4404534210
- Semantic Scholar
- 1e909e2a8cdacdcdff125ebcc566f37cb869a1c8
- Cited by
- 4,688
- References
- 229
- Citations by year
- 2026: 2433 · 2025: 1643
- FWCI
- 504.87
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Transactions on Information Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- LLM hallucination, large language models, hallucination taxonomy, hallucination detection, hallucination mitigation, retrieval-augmented generation, information retrieval systems, factual reliability, large vision-language models, knowledge boundaries
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-27, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-27 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.