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 601–700 of 2,242
Bansal, R., Chandra, R., & Lulla, K. (2025) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.2471 · Cited by 5
“Large language models (LLMs) are a major technological development that quickly moved from research labs to useful applications in corporate settings [1].”
InsightAI: Root Cause Analysis in Large Log Files with Private Data Using Large Language Model
Ekhlasi, M., Prakash, A., Lamothe, M., & Dagenais, M. (2025) · IEEE/ACM International Conference on AI Engineering – Software Engineering for AI (CAIN) · doi:10.1109/cain66642.2025.00012 · Cited by 5
Ubiquity of LLM Hallucinations Across Critical Domains: A Survey
Singh, D., & Singh, A. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8197-6_9 · Cited by 8
When DeepSeek-R1 meets financial applications: benchmarking, opportunities, and limitations
Liu, S., Chen, L., Yan, J., Jiang, Y., Wang, X., Li, X., & Yang, Q. (2025) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2500227 · Cited by 8
Intent-Based End-to-End Explainability Orchestration Framework for AI-Native Networks
Bilgin, B., Aktaş, S., & Bas, S. (2025) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft64993.2025.11080599 · Cited by 2
“Despite of the promising applications, LLM models’ reliability can be compromised by inherent challenges, such as hallucination, where models generate plausible but incorrect or misleading information [10].”
Chang, H.-S., Peng, N., Bansal, M., Ramakrishna, A., & Chung, T. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00757 · Cited by 29
Pedagogy-Driven Evaluation of Generative AI-Powered Intelligent Tutoring Systems
Maurya, K. K., & Kochmar, E. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-99261-2_3 · Cited by 10
Incorporating RAG for Factual Hallucination Detection Modeling in Intelligent Educational system
Zheng, L., Ye, J., Zhao, G. L., Luo, S., Nan, M., & Xie, Y. (2025) · International Conference on Computer Science and Technologies in Education (CSTE) · doi:10.1109/cste64638.2025.11092000 · Cited by 4
“In educational scenarios, factual hallucination may lead to the dissemination of erroneous knowledge, reduce system credibility, and pose potential risks in certain specialized areas, thus seriously affecting learning outcomes and cognitive development [4] .”
Michael, R., Kutza, J.-O., Werth, P., Liebe, J.-D., & Schöning, J. (2025) · IEEE International Symposium on Ethics in Engineering, Science, and Technology (ETHICS) · doi:10.1109/ethics65148.2025.11098302 · Cited by 2
“Within this context, [35] caution to be aware of the phenomenon of hallucinations , a common occurrence where LLMs generate plausible yet inaccurate or false information [36], which could prove catastrophic if not adequately reviewed.”
Multi-modal multi-agent debate-based dialectical knowledge transfer learning
Wang, H., Yu, W., Du, X., Chen, Q., Chu, Z., Yan, L., Jiang, J., & Guan, Y. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113551 · Cited by 4
Self-citationPersonalized Mental Health Assistance with Large Language Models
Shafi, F. R., Hossain, M. A., & Choudhury, S. (2025) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac65507.2025.00109 · Cited by 3
“Fourth, LLMs are prone to hallucination and produce fabricated or misleading information that can undermine trust and safety in clinical applications [12], [26], [29].”
Big Loop and Atomization: A Holistic Review on the Expansion Capabilities of Large Language Models
Hu, Z., Huang, Y., Feng, J., & Deng, C. (2025) · Applied Sciences · doi:10.3390/app15179466 · Cited by 4
Explainable Machine Learning for Characterizing Unknown Molecular Structures in Infrared Spectra
Na, G. S., & Rho, Y. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.5c03126 · Cited by 4
GANPrompt: Improving LLM-Based Recommendations with GAN-Enhanced Diversity Prompts
Li, X., Zhao, C., Zhao, H., Wu, L., He, M. X., & Jianping Fan, B. (2025) · ACM Transactions on Information Systems · doi:10.1145/3769428 · Cited by 13
A framework to synthetically generate fine-grained hallucinated data
Saxena, A., Aggarwal, D., Badathala, N., & Bhattacharyya, P. (2025) · Language Resources and Evaluation · doi:10.1007/s10579-025-09864-x · Cited by 6
Retrieval-Augmented Generation for Software Requirement-Based Test Case Generation
Wang, Z., Guo, X., & Tsuchiya, T. (2025) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs65678.2025.00022 · Cited by 6
“Traditional LLMs generate responses based solely on learned parameters and stored knowledge, which often results in limited accuracy[28], hallucinations[16], [18], [17], or outdated information[29].”
Du, B., Kang, X., Xu, H., Wu, Y., & Liu, Y. (2025) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs65678.2025.00016 · Cited by 3
“RAG retrieves historical fault cases from external knowledge bases, providing accurate contextual information and improving model generalization [7].”
Visual Foundation Models for Archaeological Remote Sensing: A Zero-Shot Approach
Landauer, J., & Klassen, S. (2025) · Geomatics · doi:10.3390/geomatics5040052 · Cited by 4
“This phenomenon, common among foundation models [31], refers to evidently incorrect or implausible outputs such as detections in locations devoid of any archaeological features, whose underlying causes are not yet fully understood.”
Bai, B., Meng, X., & Zhao, C. (2025) · Applied Sciences · doi:10.3390/app151910850 · Cited by 7
Souza, G. D. P., Melo, G., & Schneider, D. (2025) · Informatics · doi:10.3390/informatics12040113 · Cited by 3
Liu, B., Xu, L., Ren, B., Yu, C., Yu, H., Chen, X., & Liu, X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112733 · Cited by 2
LLMs and NLP integration enables ion irradiation-induced swelling prediction in stainless steels
Zhou, J., Wang, W., Jiang, X. F., Bai, B., & Su, Y. (2025) · Journal of Nuclear Materials · doi:10.1016/j.jnucmat.2025.156241 · Cited by 2
Large language model augmented joint learning framework for entity-relation extraction
Zou, H., Wang, Y., & Huang, A. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114094 · Cited by 2
Edge Intelligence in the Generative Artificial Intelligence Era
Zhang, X., Xie, G., Huang, Y., Xiong, Z., Liu, J., Cui, S. R., Sun, S., & Shen, X. (2025) · IEEE Wireless Communications · doi:10.1109/mwc.2025.3599652 · Cited by 5
“Additionally, the cloud lacks adequate and up-to-date data to train new GAI models, which leads to output hallucinations that are inconsistent with real-world facts [4].”
Test Performance of Artificial Intelligence in the Chinese Social Work Certification Examination
Zhao, J., Qin, T.-Y., & Shen, L. (2025) · Research on Social Work Practice · doi:10.1177/10497315251389554 · Cited by 4
“The theme of neglecting the instruction of multiple-choice question is akin to instruction inconsistency, which suggests that AI ’ s outputs derive from a user ’ s directive (Huang et al., 2025).”
InfluentialEvaluation of geographical distortions in language models
Decoupes, R., Interdonato, R., Roche, M., Teisseire, M., & Valentin, S. (2025) · Machine Learning · doi:10.1007/s10994-025-06916-9 · Cited by 8
“…correspond to plausible yet nonfactual content (Huang et al., 2025) generated by an LM. Inherent biases in pretraining data can lead to inequalities in information representation and contribute to knowledge gaps, ultimately resulting in data-related hallucinations (Huang et al., 2025).”
Huang, B., Dong, Z., & Dou, J. (2025) · SAGE Open · doi:10.1177/21582440251392110 · Cited by 5
“To mitigate the inherent ‘‘hallucination’’ problem that can erode user trust (Huang et al., 2025), technical interventions are important.”
HCLeK: Hierarchical Compression of Legal Knowledge for Retrieval-Augmented Generation
Yang, J., Liu, H., Yuan, M., Hu, Y., Liu, Y., Shen, W., & Kao, B. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3760925 · Cited by 2
Wei, Z., Wang, S., Rong, X., Liu, X., & Li, H. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4088-4_32 · Cited by 13
Barlow, S. H., Chicklore, S., He, Y., Sebastien Ourselin, A., Wagner, T., Barnes, A., & Cook, G. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1702082 · Cited by 3
“LLMs can hallucinate, where they generate incorrect but seemingly plausible content (51), an issue of concern in the healthcare domain (52).”
Man-Made Heuristics Are Dead. Long Live Code Generators!
Dwivedula, R., Saxena, D., Akella, A., Chaudhuri, S., & Kim, D. (2025) · ACM Workshop on Hot Topics in Networks (HotNets) · doi:10.1145/3772356.3772413 · Cited by 13
VALID-Mol: A Systematic Framework for Validated LLM-Assisted Molecular Design
Malikussaid, Nuha, H. H., & Kurniawan, I. (2025) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs68724.2025.11382717 · Cited by 7
Fine-Tuned Large Language Models for Logical Translation: Reducing Hallucinations with Lang2Logic
Pan, M., Kodakandla, D., & Farooque, M. (2025) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc66965.2025.11250432 · Cited by 2
“Hallucination [4] in language models represents a phenomenon where, based on memorized training data patterns, the model generates outputs containing fabricated, plausible-sounding information when confronted with unseen scenarios.”
AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
Hu, H., Chen, P., Zhao, Y., & Chen, Y. (2025) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3719027.3765064 · Cited by 42
SHERPA: A Model-Driven Framework for Large Language Model Execution
Chen, B., Chene, K., López, J. A. H., Mussbacher, G., Varró, D., & Feizpour, A. (2025) · ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) · doi:10.1109/models67397.2025.00024 · Cited by 7
“However, the stochastic nature of LLMs raises significant concerns around the potential hallucination in the generated outputs [11].”
Probably Correct: Rethinking Formal Verification for LLM-Driven Systems
Bhardwaj, A., & Fomina, S. (2025) · IEEE International Conference on Cyber Security and Cloud Computing (CSCloud) · doi:10.1109/cscloud66326.2025.00020 · Cited by 2
“This stochasticity can introduce inconsistencies, hallucinations [26], or subtle logical flaws.”
Zheng, J., Liu, Z., Li, C., et al. (2025) · Applied Sciences · doi:10.3390/app152312782 · Cited by 2
Precedent Aware Legal Reasoning System for Turkish Jurisdiction with RAG Supported LLMs
Genç, U., Keskin, Ö. F., Akman, N. P., Berkol, A., & Birant, D. (2025) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit67332.2025.11267996 · Cited by 4
“However, they are prone to hallucination—the generation of factually unsupported content—which undermines their reliability in domains where accuracy and verifiability are critical [3].”
Clinical evaluation of GenAI adaptive cancer therapy
Derbal, Y. (2025) · EngMedicine · doi:10.1016/j.engmed.2025.100116 · Cited by 3
Privacy protection in RAG: A novel method and evaluation framework
Zhang, Y., Wu, J., Li, R., Zhang, T., Song, Y., Li, C., Wang, S., Shen, H., Yin, J., Ge, J., et al. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104505 · Cited by 10
Virvou, M. K., Tsihrintzis, G. A., Marinakis, V., Sarmas, E., Panagoulias, D. P., & Tsichrintzi, E.-A. (2025) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai66417.2025.00025 · Cited by 2
“Evaluations of LLMs, such as ChatGPT [10], show high fluency but limited factual reliability across domains [11].”
Li, P., Hu, Y., Li, J., Gemeinhardt, G., Li, F., Amith, M. “., Cui, L., Forte, A. J., & Tao, C. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.12.007 · Cited by 5
“This enables temporal fidelity as recommendations evolve and provides verifiable provenance for audit and clinician oversight, reducing unsupported statements in domains where high-quality data are scarcer than general web corpora [34–36].”
Med-TAMARA: Trust-Aware Multi-Agent Risk Assessment in Medical AI Dialogue
Wu, J.-Y., & Day, M.-Y. (2025) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri66576.2025.00052 · Cited by 2
“These issues include both factual inaccuracies and misalignment with user intent [7], [8].”
Luo, X., Chen, Y., Tu, Y., & Qiu, W. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114976 · Cited by 4
Trustworthy Information Retrieval in the LLM Era: Bias, Unfairness, and Hallucination
Dai, S., Xu, C., Xu, S., Sun, Z., Pang, L., Dong, Z., & Xu, J. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769670 · Cited by 5
Rethinking sepsis prediction in the era of large language models
Wong, A., Singh, K., & Nemati, S. (2026) · npj Health Systems · doi:10.1038/s44401-025-00062-z · Cited by 4
Recent Progress in Deep Learning for Chest X-Ray Report Generation
Salhi, M., & Akhloufi, M. A. (2026) · BioMedInformatics · doi:10.3390/biomedinformatics6010003 · Cited by 6
Xiong, Y., Ge, J., & Che, L. (2026) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2026.3654823 · Cited by 2
“(3) In terms of the “hallucination”, it includes two aspects: “structural hallucination” and “parametric hallucination” [5].”
Administrative Decision-Making with Generative AI: The Challenge of Epistemic Boundedness
Kim, Y., Kim, J., Kim, T., & Cho, H.-C. (2026) · Administration & Society · doi:10.1177/00953997251409156 · Cited by 5
“They can generate plausible but irrelevant, fabricated, or inaccurate content, commonly referred to as “hallucinations” (see Huang et al., 2025; Kalai et al., 2025).”
Explainability in Digital Twins: Overview and Challenges
Mahmoud, M., & Lazarova‐Molnar, S. (2025) · Winter Simulation Conference · doi:10.1109/wsc68292.2025.11338898 · Cited by 4
“Computational demands (Yang et al. 2025) potential for hallucinations due to inadequate domain adaptation (Huang et al. 2025) pose significant challenges that can undermine user trust.”
iKnow: an Intent-Guided Chatbot for Cloud Operations with Retrieval-Augmented Generation
Huang, J., Zhong, Y., Yu, G., Jiang, Z., Yan, M., 栾文飞, Yang, T., Ren, R., & Lyu, M. R.-T. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00084 · Cited by 2
“Nonetheless, relying solely on LLMs poses challenges such as the hallucination and the inability to access to timely and proprietary data [11], [12].”
Generalist multimodal AI: A review of architectures, challenges and opportunities
Munikoti, S., Stewart, I., Horawalavithana, S., Kvinge, H., Emerson, T., Thompson, S., & Pazdernik, K. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132933 · Cited by 9
xu, Q., Zhang, C., Ma, D., Cao, Y., & Zhou, G. (2026) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2026.103254 · Cited by 4
Towards Secure Retrieval-Augmented Generation: Preventing LLM Data Leaks with RBAC
Martinelli, I., & Ponti, M. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15993-9_34 · Cited by 5
Scantamburlo, T., & Zollo, F. (2026) · ACM Transactions on the Web · doi:10.1145/3796546 · Cited by 4
Bai, T., Jiang, K., Yu, Y., Qie, S., Wang, C., Wang, B., & Zhang, W. (2026) · Future Internet · doi:10.3390/fi18020095 · Cited by 2
“Here, hallucination denotes generated statements containing fabricated or clinically incorrect facts (e.g., nonexistent history, wrong contraindications, or spurious citations) not supported by the input or verifiable evidence [94].”
Thùy, P. T., & Thảo, L. T. (2026) · Reflective Practice · doi:10.1080/14623943.2026.2631417 · Cited by 3
“…trust in AI-generated suggestions, particularly because LLMs can produce fluent but nonfactual or misleading content (‘hallucinations’), which may distort inquiry unless teachers actively verify and contextualize claims (Huang et al., 2025; Kasneci et al., 2023; Lee & See, 2004; Nissenbaum, 2004).”
Enabling natural language analysis for object-centric event logs
Casciani, A., Bernardi, M. L., Cimitile, M., & Marrella, A. (2026) · Process Science · doi:10.1007/s44311-026-00037-9 · Cited by 2
“Yet, challenges persist in ensuring accurate and contextually relevant responses from LLMs due to potential biases and outdated knowledge inherited from the training data (Gao et al. 2023; McK-enzie et al. 2023) and hallucinations (Huang et al. 2025).”
Hallucinated intelligence? Cognitive and emotional pathways to generative AI reuse
Liu, C., Cong, Y., & Zhang, Z. (2026) · Aslib Journal of Information Management · doi:10.1108/ajim-05-2025-0252 · Cited by 7
Revealing the True Indicators: Understanding and Improving IoC Extraction From Threat Reports
Froudakis, E., Avgetidis, A., Frankum, S. T., Perdisci, R., Antonakakis, M., & Keromytis, A. D. (2025) · 2025 IEEE Annual Computer Security Applications Conference (ACSAC) · doi:10.1109/acsac67867.2025.00052 · Cited by 2
“LLM-based approaches are prone to hallucinations and are limited by their context window [9], [10], [11], [36], [37].”
Ju, Y.-J., Wang, Y., Chou, F., Hou, W., Chen, S., & Hsieh, C. (2026) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2026.02.011 · Cited by 3
Medical multi-recall embedding: Adaptive retrieval for diverse evidence in medical RAG systems
Li, C., Jing, F., Li, H., Dong, Z., Xu, Z., Zou, H., Wang, Q., He, J., Qian, Y., Cao, B., et al. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104695 · Cited by 4
Enhancing Cognitive Diagnosis via LLM-Driven Heterogeneous Concept Graph Construction
Sheng, Y., Tang, J., Zeng, W., Zhao, X., & Tan, Y. (2026) · Engineering · doi:10.1016/j.eng.2026.02.017 · Cited by 2
Chen, Y., Chen, M., Zhu, Y., Pei, J., Chen, S., Zhou, Y., (32470), Y. W., Zhou, Y., (31608), H. L., & Zhang, S. (2026) · Journal of Web Semantics · doi:10.1016/j.websem.2026.100879 · Cited by 12
Generative AI as a Knowledge Distribution System
Lavazza, A., & Farina, M. (2026) · Social Epistemology · doi:10.1080/02691728.2026.2623557 · Cited by 4
Shehmir, S., & Kashef, R. F. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1735253 · Cited by 2
Ademolu, E. (2026) · AI & Society · doi:10.1007/s00146-026-02956-4 · Cited by 3
“Systems such as ChatGPT, developed by OpenAI, generate human-like text through probabilistic pattern recognition across vast linguistic corpora (Cohen et al. 2024; Huang et al. 2025).”
InfluentialLanguage Without Propositions: Why Large Language Models Hallucinate
Mácha, J. (2026) · Philosophies · doi:10.3390/philosophies11020042 · Cited by 4
“To position propositional interpretability, Chalmers invokes the distinction between the basic/ground layer and middle layer in LLMs’ design.”
OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning
Hoveyda, M., Piepenbrock, J., de Vries, A. P., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21289-4_7 · Cited by 2
Díaz, G. M. C., Jiménez‐Leal, W., Grisales, M. A., Sripada, C., Amaya, S., Inzlicht, M., & Bermúdez, J. P. (2026) · Behavior Research Methods · doi:10.3758/s13428-026-02966-6 · Cited by 6
“For example, several studies have examined LLM hallucinations: fabricated outputs that, although seemingly plausible, diverge from the given input, its context, or conventional knowledge (Liu et al., 2024; Zhang et al., 2025; Huang et al., 2025).”
Urban traffic evaluation with social media data: A consensus-based LLM negotiation paradigm
Li, M. M., Fan, C., Yan, H., 武鹏凯, Su, Z., & Ma, W. (2026) · Transportation Research Part A Policy and Practice · doi:10.1016/j.tra.2026.104980 · Cited by 2
Self-citationAdvancing adversarial and LLM robustness in trustworthy AI: a comprehensive survey
Tang, Q., Qian, J., Du, X., Wang, S., & Liu, H. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11558-x · Cited by 4
He, K., Wu, J., & Wang, C. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104773 · Cited by 2
Cheng, F., Li, Q., He, L., Li, H., Brooks, B. W., Yu, Z., & You, J. (2026) · Environmental Science & Technology · doi:10.1021/acs.est.6c01342 · Cited by 4
Can LLMs Automate Fact-Checking Article Writing?
Sahnan, D., Corney, D. P. A., Larraz, I., Zagni, G., Míguez, R., Xie, Z., Gurevych, I., Churchill, E. F., Chakraborty, T., & Nakov, P. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.644 · Cited by 12
Cabezas-Clavijo, Á., & Sidorenko-Bautista, P. (2026) · Journal of Data and Information Science · doi:10.1515/jdis-2025-0326 · Cited by 22
“This capacity relies on deep learning and neural networks, which enable the simulation of human output with increasingly realistic results (Ray, 2023).”
Physics-informed multimodal large model for machine fault diagnosis with dynamic vision
Lu, Z., Li, X., Liu, C., & Yu, S. (2026) · Structural Health Monitoring · doi:10.1177/14759217261445117 · Cited by 6
Explainable autonomous cyber defense using adversarial multi-agent reinforcement learning
Zhang, Y., Goel, D., & Ahmad, H. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132741 · Cited by 2
“Recent surveys on LLM-based autonomous cyber agents and hallucination behavior further indicate that unconstrained agent reasoning can amplify operational risk under uncertainty [21], [22].”
Zhu, Z., Zhang, J., Zhao, S., et al. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.126059 · Cited by 2
Hu, L., Wang, H., Xiang, T., Chen, Z. H., He, J., & Guo, S. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3694035 · Cited by 2
“By retrieving contextually relevant text chunks prior to response generation, RAG enhances factual integrity, supports continual learning from evolving environments, and enables embodied agents to operate reliably under uncertainty [10], [11], [12], [13].”
Self-citationDennison, D. V., Ahtisham, B., Chourasia, K., Arora, N., Singh, R., Kizilcec, R. F., Nambi, A., Ganu, T., & Vashistha, A. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3788074 · Cited by 37
Gao, Z., & Thebault-Spieker, J. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3788058 · Cited by 2
Islam, M. S., Hoque, T., Shuvo, J. I., Tori, S. R., Malitha, S. B., Alam, M. Z., & Chowdhury, A. K. A. (2026) · InfoScience. · doi:10.1002/inc2.70011 · Cited by 2
“311 These models often produce outputs that look convincing but are factually wrong.”
Jin, C. (., Kim, J., & Im, J. (2026) · Tourism Management · doi:10.1016/j.tourman.2026.105468 · Cited by 3
Breaking the “80-point ceiling”: librarians as facilitators of LLM clean-up engineering
Li, R. (2026) · The Journal of Academic Librarianship · doi:10.1016/j.acalib.2026.103273 · Cited by 3
Qi, Z., Yang, Z., Liu, M., & O’Neill, Z. D. (2026) · Advances in Applied Energy · doi:10.1016/j.adapen.2026.100283 · Cited by 3
Three inseparable facets and five new knowledge domains: An extended GenAI-TPACK proposal
Demir, S., Uşak, M., & Кодиров, О. С. (2026) · Pedagogical Research · doi:10.29333/pr/18714 · Cited by 5
“Huang et al. (2025) describe how large language models generate content that deviates from user input, contradicts prior context, or conflicts with established world knowledge.”
Chen, J. B., Witold Pedrycz, C., Wang, F., Wu, J. D., Wu, G., Xing, L., Chen, Y., & Song, Y. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3700605 · Cited by 4
“Nevertheless, due to the interference of hallucinations [41] and the complexity of EOSTSP, deploying LLMs for its resolution introduces profound challenges.”
A Novel Hierarchical Multi-agent System for Payments Using LLMs
Chua, J. K., Huang, D., & Wang, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1462-4_3 · Cited by 2
“Nonetheless, the risk of LLM hallucinations pose a challenge to agentic reliability [8, 10, 24].”
Security Risks and Mitigation Strategies for Large Language Models in Power Systems: A Review
Chen, X., Shi, J., & Lu, H. (2026) · Electricity · doi:10.3390/electricity7020054 · Cited by 4
RC-RAG: A Reliability-Centered Retrieval-Augmented LLM Framework for PHM Question Answering
Su, H., Wang, R., Ji, D.-Y., & Lee, J. (2026) · IEEE Transactions on Reliability · doi:10.1109/tr.2026.3702056 · Cited by 3
Hilkenmeier, F., Stoltenberg, M., & Stierle, C. M. G. (2026) · Systematic Reviews · doi:10.1186/s13643-026-03228-4 · Cited by 8
“In this sense, the task is less affected by performance degradation associated with longer or more complex input contexts [49] and less reliant on the kind of open-ended generation in which hallucinated content is more likely to arise [16, 35, 37].”
Melville, G., Ghiassi, D., Inthathirath, S., et al. (2026) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2026.198013 · Cited by 2
Lau, G. R., Kasturiratna, K. T. A. S., Goh, A. Y. H., Tong, E. M. W., & Hartanto, A. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101186 · Cited by 18
Cairang, Z., Shi, C., Ou, H., Wu, Y., Fang, D., & Li, W. (2026) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2026.153254 · Cited by 4
Han, S. (2026) · TechTrends · doi:10.1007/s11528-026-01208-y · Cited by 2
“However, their outputs are fundamentally shaped by statistical pattern matching, not necessarily grounded comprehension, which introduces well‑documented challenges related to factual reliability, hallucination, and overconfidence (Du et al., 2024; Huang et al., 2025; Martino et al., 2023).”
Large language models in model-driven engineering: a systematic mapping study
Zhang, W., Jiang, B., Yuhong, F., Cheng, H., Hummel, M., Scotti, V., Hagel, N., Li, J., Großmann, G., Stumptner, M., et al. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10921-4 · Cited by 6
“[52, 63, 66] Metrics: adequacy score; hallucination rate [52]; human preference score; inter-rater agreement [23, 68].”
Wang, R., Tong, Y., & Zhuang, C. (2026) · Computers & Industrial Engineering · doi:10.1016/j.cie.2026.112246 · Cited by 2
Byun, H., Lee, D., Jung, M., & Jang, B. (2026) · Journal of Medical Systems · doi:10.1007/s10916-026-02440-y · Cited by 3
Safety and security of large language models in healthcare
Clusmann, J., Freyer, O., Ostermann, M., Ferber, D., Laleh, N. G., Hilgers, L., Kolbinger, F. R., Schneider, C. V., Downing, A., Wekenborg, M., et al. (2026) · Nature · doi:10.1038/s41586-026-10687-1 · Cited by 8
“Causes for hallucinations can be broadly separated into hallucinations by data, training or inference 113 .”
Influential
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.