A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
Open accessThe 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.
Abstract
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 501–600 of 2,245
Personalized Non-Player Characters: A Framework for Character-Consistent Dialogue Generation
Liu, X., Xie, Z., & Jiang, S. (2025) · AI · doi:10.3390/ai6050093 · Cited by 3
“…research mainly relies on the problem recognition capability of Large Language Models (LLMs), but traditional sequence-to-sequence architectures are prone to introducing noise and, influenced by the “hallucination” problem [10], may lead to relationship recognition errors or entity omissions.”
Human-inspired Perspectives: A Survey on AI Long-term Memory
He, Z., Lin, W., Zheng, H., Zhang, F., Jones, M. W., Aitchison, L., Xu, X., Liu, M., Kristensson, P. O., & Shen, J. (2024) · arXiv · doi:10.48550/arxiv.2411.00489 · Cited by 3
“It can be used to extend the context of AI systems, shape AI systems’ behavioral strategies, and serve as training samples to prevent catastrophic forgetting.”
LLM-Based Text Style Transfer: Have We Taken a Step Forward?
Toshevska, M., & Gievska, S. (2025) · IEEE Access · doi:10.1109/access.2025.3548967 · Cited by 22
“Producing hallucinations could be a result of various factors [23].”
Alabdulwahab, A., Japic, C., Le, C., Dubey, D., Trivedi, D., Hope, J., Stone, P., Srivastava, S., Tashman, A. P., & Zhang, A. (2025) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds65500.2025.11021089 · Cited by 6
“Hallucination refers to the generation of content that is non-sensical or factually inconsistent with the source material [5].”
Exploring Large Language Models for Analyzing Open Source License Conflicts: How Far Are We?
Cui, X., Wu, J., Ling, X. G., Luo, T., Yang, M., & Ou, W. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse-companion66252.2025.00083 · Cited by 11
“Despite zero-shot solid capabilities, the model frequently generates irrelevant terms due to a lack of domain-specific fine-tuning, leading to significant hallucination [14] and reduced accuracy.”
Comparison of explainability methods for hallucination analysis in LLMs
Papagiannopoulos, I., Koutalidis, H., Rempi, P., Ntanos, C., & Askounis, D. (2025) · Open Research Europe · doi:10.12688/openreseurope.20839.1 · Cited by 7
Attention economics, artificial intelligence, and the future of the planning profession
Metzger, J. (2025) · Planning Theory · doi:10.1177/14730952251360224 · Cited by 4
“Hallucinations appear not to be evenly distributed but occur more commonly in relation to certain types of prompts and knowledge areas (Huang et al., 2025) – and according to my own experience, academic references appear to be a particular Achilles heel.”
SkyNet: Analyzing Alert Flooding from Severe Network Failures in Large Cloud Infrastructures
Yang, B., Hu, H., Li, Y., Li, Y., Tang, X., Tian, B., Wu, G., Xu, J., Zhang, X., Chen, F., et al. (2025) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/3718958.3750536 · Cited by 9
Integrating External Knowledge with LLMs: A Systematic Review of RAG Approaches
Mikulić, I., Vlaić, M., Delač, G., Šilić, M., & Vladimir, K. (2025) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro65660.2025.11131735 · Cited by 6
“Despite their capabilities, LLMs face challenges such as hallucinations [8], where they generate factually incorrect or outdated information.”
Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation
Xu, Q., Wang, G., Briand, L., & Liu, K. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3803418 · Cited by 24
Exploiting knowledge graph communities to fine-tune large language models
Amelio, A., Buratti, C., Marchetti, M., Traini, D., Ursino, D., & Virgili, L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129816 · Cited by 7
Wang, M., Shen, Y., Zhao, B., Zhou, X., Sun, L., & Liu, X. (2025) · Health Information Science and Systems · doi:10.1007/s13755-025-00379-x · Cited by 3
Asking Questions to Alleviate Object Hallucination in Large Vision-Language Models
Bi, C., Dang, T., Wang, S., Cao, F., & Huang, Q. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3618949 · Cited by 3
“Therefore, many studies have been carried out with the aim of reducing the impact of hallucinations [29], [30], [31].”
Symbiotic agents: A novel paradigm for trustworthy AGI-driven networks
Chatzistefanidis, I., & Nikaein, N. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111749 · Cited by 5
A Graph-Based RAG for Energy Efficiency Question Answering
Campi, R., Vago, N. O. P., Giudici, M., Rodriguez-Guisado, P. B., Brambilla, M., & Fraternali, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-97207-2_4 · Cited by 3
Can generative AI detect and fix real-world cryptographic misuses?
Firouzi, E., & Ghafari, M. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112650 · Cited by 7
Whitty, M. T. (2025) · Electronics · doi:10.3390/electronics14204104 · Cited by 6
Chu, T., Chen, Y., Zhu, R., & Zeng, F. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.10.013 · Cited by 6
BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
Zhou, S., Schöner, H., Lyu, H., Fouché, E., & Wang, S. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761278 · Cited by 15
CHAIR-Classifier of Hallucination As Improver
Sun, A. (2025) · doi:10.1109/ijcnn64981.2025.11227344 · Cited by 3
“Hallucinations are a common issue in large language models (LLMs), limiting their reliability in critical applications, and a lot of research has been working on it [1] [2].”
Zhou, H., Zhu, Z., Oh, K. M., & Hong, S.-S. (2025) · JMIR Formative Research · doi:10.2196/79975 · Cited by 5
“For instance, using LLMs often fails at providing valid information [26], relevant answers based on personalized context, nonaction-able suggestions [27,28], answers that lack genuine contextual understanding and empathy [29], and answers with bias related to age, disability, and race, thereby…”
Architectural Concepts for Integrating Fundamental Drives and Emotions Into Artificial Intelligence
Ferdinan, T., Mieleszczenko-Kowszewicz, W., Kocoń, J., & Kazienko, P. (2025) · IEEE Intelligent Systems · doi:10.1109/mis.2025.3622004 · Cited by 4
Fan, Y., Shi, L., Sun, Y., & Mi, B. (2025) · Aerospace Science and Technology · doi:10.1016/j.ast.2025.110933 · Cited by 3
The AI Imitation Game: A Cognitive Comparison of Mimicry in Large Language Models
Wen, V., Peng, Z., & Chen, Y. (2025) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri66576.2025.00022 · Cited by 3
“Huang et al. categorize these hallucinations into factual and faithfulness errors, with factual presenting contradictions to real-world knowledge, while faithfulness errors emerge from deviations from given prompts [17].”
Adaptive Retrieval-Augmented Embodied Intelligence RAG Reasoning Framework
Chen, M., Bai, Y., Fang, X., & Yi, P. (2025) · IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) · doi:10.1109/seai65851.2025.11108876 · Cited by 3
“Huang et al. [11] systematically reviewed hallucination mitigation methods, including data optimization and architectural improvements.”
Tang, Y., Fang, Y., Wang, T., Sun, L., & Chen, L. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747597 · Cited by 10
Deng, L., Chen, L., Liu, M., Wang, X., Qi, Y., Shao, C., & Jiang, T. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104435 · Cited by 4
HaluGNN: Hallucination detection in large language models using graph neural network
Kong, L., Zhang, Y., Zhong, X., Fu, H., Wang, Y., & Liu, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130857 · Cited by 11
A Survey of Hallucination in Large Language Models
何, 金. (2026) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.151016 · Cited by 5
Language of images: Classifying marketing images with transformers and vision language models
Witte, M., Heitmann, M., Hartmann, J., & Tetzlaff, K. (2026) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2026.01.001 · Cited by 3
Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives
Queiroz, D., Carlos, A., Anjos, A., & Berton, L. (2026) · ACM Transactions on Computing for Healthcare · doi:10.1145/3793542 · Cited by 15
“They are typically associated with high uncertainty and incomplete or inaccurate knowledge [97, 98, 99, 100], particularly in instances where the model lacks relevant training data and exhibits low confidence [101, 102, 97].”
Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance
Rothon, C., Walker, C., Aslansefat, K., Dethlefs, N., & Papadopoulos, Y. I. (2024) · doi:10.65391/r1929 · Cited by 4
“Issues have been identified with hallucinations (Huang et al. 2023) and unsafe recommendations (Inan et al. 2023), which must be mitigated before LLM-based tools can be relied upon fully.”
iCodeReviewer: Improving Secure Code Review with Mixture of Prompts
Peng, Y. F., Kim, K., Meng, L., & Liu, K. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00264 · Cited by 9
“LLMs are not guaranteed to be reliable and could make mistakes due to hallucination [10].”
Visual Knowledge-Enhanced LLaVA for Fine-Grained Multimodal Named Entity Recognition and Grounding
Yuan, L., Cai, Y., Zhu, B., Liu, Z., Deng, Z., Li, Q., & Wang, T. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3651977 · Cited by 3
“2) Multi-LLM Consistency Visual Knowledge: Since hallucinations in LLMs [26] may cause the omission or generation of inaccurate visual knowledge associated with entities, we draw inspiration from the use of self-consistency to enhance LLM reasoning abilities [64].”
Personalised LLMs and the risks of the digital twin metaphor
Annoni, M., Battisti, D., & Marchegiani, B. (2026) · AI & Society · doi:10.1007/s00146-026-02875-4 · Cited by 6
“Second, even when the data is available in the personalized training set, LLMs are prone to hallucination (confidently producing false or misleading outputs that do not align with what is present in the training data) (Huang et al. 2025).”
BearGen: LLM-guided signal generation framework for bearing fault diagnosis
Lee, J., Jeon, H., Kim, U., & Kim, M. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104400 · Cited by 8
A Knowledge-Augmented Multistage Reasoning Approach for Wind Turbine Fault Cause Analysis
Hu, Y., Wen, P., & Dai, Y. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3658534 · Cited by 4
“Meanwhile,groundingLLMgenerationon externalknowledge,suchasKGsthroughretrieval-augmented generation(RAG),hasbeenshowntoeffectivelyreducehallu-cinationandimprovefactualreliabilityinindustrialreasoning tasks[10].”
A foundational individual mobility prediction model based on open-source large language models
Qin, Z., Wang, L., Ling, Y., Pereira, F. C., & Ma, Z. (2026) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2026.105562 · Cited by 12
Data-driven discovery of digital twins in biomedical research
Métayer, C., Ballesta, A., & Martinelli, J. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf722 · Cited by 15
“Indeed, LLMs are particularly pr one to hallucinations in underspecified settings [213], which are common in biology, making factual reliability a critical concern.”
Song, W., Nabahirwa, E., Zhang, M., Fang, Y., & Ni, Z. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-00895-z · Cited by 12
KAG: A Scalable Knowledge-Augmented Generation System for Educational Content Management
Hasan, H., Ismail, A., Mohanna, A., & Chehab, A. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391105 · Cited by 6
“Current educational platforms often lack both semantic retrieval depth and transparent attribution mechanisms [7], [8].”
Jalali, P., Wang, F., Ourang, S. A., Zahedrozegar, S., Mohammad‐Rahimi, H., & Nosrat, A. (2026) · Journal of Endodontics · doi:10.1016/j.joen.2026.02.014 · Cited by 6
Yang, Y., Jing, J., Ran, G., Wang, T., Zhang, G., Zhang, Y., Zhao, J., Ma, Y., & Li, X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114927 · Cited by 3
Jiang, Z., Zhao, R., Lin, L., Yu, Y., Chen, H., Zhang, X., Xu, X., Wang, Y., Ma, X., & Ngai, E. C. ‐. (2026) · ACM Transactions on Computing for Healthcare · doi:10.1145/3797883 · Cited by 15
Generative AI-enabled chatbots for user-centred design: a state-of-the-art review
Zhou, T., Liu, Y., Kumar, M., & Wang, S. (2026) · Journal of Engineering Design · doi:10.1080/09544828.2026.2633488 · Cited by 12
Yang, Y., Wang, Q., Li, W., Wang, S., Fang, S. F., Sun, K., Wang, S., Wang, H., Dai, X., Li, Z., et al. (2026) · International Journal of Digital Earth · doi:10.1080/17538947.2026.2640706 · Cited by 4
“However, relying solely on MLLMs for complex joint extraction tasks introduces several challenges, including hallucinations, unstable reasoning chains, and a limited ability to follow precise instructions (Huang et al. 2025; Patil and Jadon 2025).”
Self-citationAwill, R., Khan, W. A., Hussain, M., Anderson, B., & Kazmi, S. M. A. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131801 · Cited by 4
Hallucination in Generative AI-Enabled Wireless Communications: Concepts, Issues, and Solutions
Xudong, W. A. N. G., Wang, J., Feng, L., et al. (2026) · IEEE Communications Magazine · doi:10.1109/mcom.001.2500124 · Cited by 3
“The causes of hallucination are primarily associated with the model’s training methodology, limited training data, and the probabilistic nature of generative models [3].”
Ng, J. Y. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1745928 · Cited by 8
Lv, J., Liu, G., Zhou, X., & Chen, Y. (2026) · Probiotics and Antimicrobial Proteins · doi:10.1007/s12602-026-11013-x · Cited by 4
Explainable and Transparent AI Architectures
Gupta, D., Nigora, A., Gulkhayo, G., Gayratovich, E. N., Karimov, S., Otabek, M., & Kenesbaevich, S. K. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8252-4.ch011 · Cited by 3
MFND-DCL: Multimodal fake news detection based on dual contrastive learning
Minghui, Q., Guo, S., Chen, Y., Wang, C., & Ye, Z. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104812 · Cited by 3
Security and Privacy of Large Language Models: Threat Taxonomy, Ethical Implications, and Governance
Pribisalić, M., & Martinčić-Ipšić, S. (2026) · AI · doi:10.3390/ai7050152 · Cited by 9
Zhang, Z., & Valeo, C. (2026) · AI for Engineering · doi:10.3390/aieng1010005 · Cited by 6
“We need to balance this tradeoff within an acceptable level of LLM hallucination [69] for hydrological field.”
Large Language Models for Ontology Engineering: A Systematic Literature Review
Li, J., Garijo, D., & Poveda‐Villalón, M. (2026) · Semantic Web · doi:10.1177/22104968261465514 · Cited by 41
“…logic systems (Baader et al., 2017; Heindorf et al., 2022), LLM reasoning abilities remain shallow, and issues such as hallucinations, limited transparency and violations of fundamental ontological constraints persist (Huang et al., 2025; Petroni et al., 2019; West et al., 2022; Xu et al., 2025).”
Concept Disentangled Transformer for Hyperspectral Image Classification
Ahmad, M. I., Mazzara, M., Vivone, G., & Hong, D. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3715319 · Cited by 3
“Concept learning aims to organize internal features into lower-dimensional structured latent variables that mediate the prediction process and provide a more analyzable representation space [22], [23], [24].”
InfluentialZhu, P., Chen, W., Chen, D., Liu, J., Liu, Z., Liu, Y., & Lin, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5666-7_20 · Cited by 5
Kaddari, Z., Hachmi, I. E., Berrich, J., Amrani, R., & Bouchentouf, T. (2024) · Applied Computer Science · doi:10.35784/acs-2024-44 · Cited by 5
Zeng, Z., Cheng, Q., Hu, X., Liu, Z., Shen, J., & Zhang, Y. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825744 · Cited by 6
Final: Combining First-Order Logic With Natural Logic for Question Answering
Shi, J., Ding, X., Hui, S. C., Yan, Y., Zhao, H., Liu, T., & Qin, B. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3551231 · Cited by 8
“While these explanations aim to elucidate the model’s reasoning, they often fail to accurately reflect the model’s underlying beliefs and can suffer from hallucinations [59].”
Self-citationBuananta, S. E. A., Hasani, M. F., Bara, A. N., & Wijaya, H. (2024) · International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) · doi:10.1109/icimcis63449.2024.10957499 · Cited by 3
“However, LLMs face limitations, particularly in delivering real-time information and occasionally suffering from "hallucination," where they generate plausible but false or nonsensical answers [6][7].”
Stromer‐Galley, J., McKernan, B., Zaman, S., Maganur, C., & Regmi, S. (2025) · Social Science Computer Review · doi:10.1177/08944393251334977 · Cited by 10
“The ongoing concern, for example, with hallucination — where AI generates false information — likely will remain a challenge (for a review, see Huang et al., 2025).”
Zhang, L., Carter, R. A., & Lim, S. N. (2025) · Journal of Special Education Technology · doi:10.1177/01626434251349405 · Cited by 4
“Speci fi cally, AI developers should implement strategies throughout the entire development and implementation phases of LLMs, including data preparation, model training, and task performance, to minimize biases and hallucinations (Huang et al., 2024).”
AI-Assisted Autoformalization of Combinatorics Problems in Proof Assistants
Doan, L., & Nguyen, T. H. (2025) · IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER) · doi:10.1109/icse-nier66352.2025.00006 · Cited by 4
“LLMs often have the hallucination issue [29], which in this context means generating combinatoric problems that are meaningless and incorrect.”
Lee, H., An, G., & Yoo, S. (2025) · International Workshop on Large Language Models for Code (LLM4Code) · doi:10.1109/llm4code66737.2025.00020 · Cited by 12
“Given that LLMs can hallucinate [14], augmenting LLM-based inconsistency checking with a more concrete exploration of program behavior seems to be a missed opportunity.”
Shao, R., Tang, Y., Yang, L., & Wang, F. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128612 · Cited by 6
IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models
Imtiaz, S. M., Singh, A., Batole, F., & Rajan, H. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3715775 · Cited by 5
A Hybrid Neuro-Symbolic Pipeline for Coreference Resolution and AMR-Based Semantic Parsing
Papakostas, C., Troussas, C., Krouska, A., & Sgouropoulou, C. (2025) · Information · doi:10.3390/info16070529 · Cited by 6
Bessa, R. F., de Oliveira, A. C., Bessa, R. F., Sousa, D. L., Alves, R., Barbosa, A., Carneiro, A., Soares, C., & Teles, A. S. (2025) · Applied Sciences · doi:10.3390/app15137134 · Cited by 4
Signé, Q., Boughanem, M., Moreno, J. G., & Belkacem, T. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744624 · Cited by 7
ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models
Chen, H., LV, K., Hu, C., Li, Y., Yuan, Y., He, Y., Zhang, X., Liu, L., Liu, S., Su, W., et al. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737374 · Cited by 19
HyLLM-IDS: A Conceptual Hybrid LLM-Assisted Intrusion Detection Framework for Cyber-Physical Systems
Muhammad, M., Shaaban, A. M., German, R., & Sardy, L. A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02018-5_10 · Cited by 7
Liu, J., Zhou, T., Chen, Y., Zhao, J., & Liu, K. (2025) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew67478.2025.00019 · Cited by 11
“However, LLMs still face issues of hallucination and lack of specific domain knowledge when dealing with complex problems [6], [7].”
Chen, Z., & Liu, B. (2025) · Information · doi:10.3390/info16090792 · Cited by 3
“When confronted with complex queries, LLMs are prone to generating “hallucinatory” responses, fabricating non-existent literature sources or misinterpreting academic viewpoints [13].”
Mawardi, V. C., Trilaksono, B. R., & Purwarianti, A. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157494 · Cited by 4
Accessibility Scout: Personalized Accessibility Scans of Built Environments
Huang, W. A., Su, X. K., Froehlich, J. E., & Zhang, Y. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747624 · Cited by 11
Examining Age-Bias and Stereotypes of Aging in LLMs
Dewan, S., Shaikh, I., Shaw, C., Sahoo, A. K., Jha, A., & Pradhan, A. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3746464 · Cited by 6
Chen, Z., Wen, J., Li, T. J.-J., Yao, Y., & Li, T. (2025) · doi:10.1145/3733816.3760759 · Cited by 4
Automated Functionality and Security Evaluation of Large Language Models
Ding, M., Shen, Y. J., & Chen, M. (2024) · IEEE International Conference on Smart Cloud (SmartCloud) · doi:10.1109/smartcloud62736.2024.00014 · Cited by 3
“LLMs [2] have extremely high abilities in understanding intentions and executing tasks, but problems such as hallucination [3] and toxicity [4] also bring instability.”
BackgroundKobayashi, K., Takamizawa, Y., Miyake, M., Ito, S., Gu, L., Nakatsuka, T., Akagi, Y., Harada, T., Kanemitsu, Y., & Hamamoto, R. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102929 · Cited by 8
Understanding and Modeling Job Marketplace with Pretrained Language Models
Zhu, Y., Wu, L., Zhang, B., Wang, S., Guo, Q. S., Hong, L., Simon, L., & Li, J. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3680036 · Cited by 8
Process Knowledge Graphs (PKG): Towards unpacking and repacking AI applications
Daga, E. (2024) · Journal of Web Semantics · doi:10.1016/j.websem.2024.100846 · Cited by 4
Bosco, C., Shojaei, F., Theisz, A. A., Nguyen, V. V., Song, H., Han, R., Torres, J. O., Peng, X., Lin, J., Chheda, D., et al. (2025) · ACM Transactions on Computing for Healthcare · doi:10.1145/3712295 · Cited by 6
Lotfi, I., Alabbasi, N., & Alhussein, O. (2025) · IEEE Internet of Things Magazine · doi:10.1109/miot.2025.3576260 · Cited by 3
Terminators: Terms of Service Parsing and Auditing Agents
Mridul, M. A., Kang, I., & Seneviratne, O. W. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3720554.3736183 · Cited by 4
Liu, H., Yin, S., Hu, X., Deng, M., Yang, X., & Xu, G. (2025) · Applied Sciences · doi:10.3390/app15169012 · Cited by 3
Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems
Vandeputte, F. (2025) · ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software (Onward!) · doi:10.1145/3759429.3762620 · Cited by 9
SAM-RAG: An Self-adaptive Framework for Multimodal Retrieval-Augmented Generation
Zhai, W. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227819 · Cited by 5
“Retrieval quality is critical for RAG, as irrelevant documents induce hallucinations [25].”
The Impact of LLM Adoption on Online User BehaviorPreprint
Padilla, N., Lam, H. T., Lambrecht, A., & Hollenbeck, B. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5393256 · Cited by 23
Xia, S.-J., Zhang, H., Jiang, Y., Chen, X., Chen, Y., Li, Z., Wan, Z., & Sun, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5731427 · Cited by 4
Chen, W.-C., & Chen, S.-Y. (2026) · IEEE Access · doi:10.1109/access.2026.3658502 · Cited by 3
“Finally, mixed-quality training data can induce hallucinations in LLMs, leading to unnecessary energy consumption and poor performance in critical tasks [49].”
Large Language Model Reasoning Failures
Song, P., Han, P., & Goodman, N. (2026) · arXiv · doi:10.48550/arxiv.2602.06176 · Cited by 3
Xie, E., Cheng, L., Shireman, J., Cai, Y., Liu, J., Mohanty, C., Dey, M., & Kendziorski, C. (2024) · doi:10.1101/2024.12.04.626476 · Cited by 3
Towards Safer Heuristics With XPlain
Karimi, P., Pirelli, S., Kakarla, S. K. R., Beckett, R., Segarra, S., Li, B., Namyar, P., & Arzani, B. (2024) · ACM Workshop on Hot Topics in Networks (HotNets) · doi:10.1145/3696348.3696884 · Cited by 8
Enhancing functional gene set analysis with large language models
(2024) · Nature Methods · doi:10.1038/s41592-024-02526-w · Cited by 2
Fan, Z., Chen, C., & Luo, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127434 · Cited by 2
Text–image fusion template for large language model assisted crowdsourcing test aggregation
Zhu, Y., Yu, S., Zong, Z., Wang, Y., Zhao, Y., & Chen, Z. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112478 · Cited by 2
An Architecture and Protocol for Decentralized Retrieval Augmented Generation
Hecking, T., Sommer, T., & Felderer, M. (2025) · IEEE International Conference on Software Architecture Companion (ICSA-C) · doi:10.1109/icsa-c65153.2025.00012 · Cited by 5
“In such cases, LLMs tend to produce answers that may sound reasonable but are far away from the truth, which is referred to hallucination effects [3].”
ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data
Ilg, N., Pfitzenmaier, M., Germek, D., Duplys, P., & Menth, M. (2025) · IEEE Access · doi:10.1109/access.2025.3575258 · Cited by 2
“Encoded payloads, even basic Base64, raised difficulties, especially for smaller models, and in some cases even caused logical hallucinations [10] for larger ones.”
Teaching Things To Think: Bootstrapping Local Reasoning for Smart(er) Devices
King, E., Yu, H., Vartak, S., Jacob, J., Lee, S., & Julien, C. (2025) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom64205.2025.00027 · Cited by 3
“While limits exist [10], LLMs nonetheless introduce flexibility to human-machine interactions: they are now used to, e.g., control smart homes [11], [12].”
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.