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
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
Tran, K.-T., Dao, D., Nguyen, M.-D., Pham, Q.-V., O'Sullivan, B., & Nguyen, H. D. (2025) · arXiv · doi:10.48550/arxiv.2501.06322 · Cited by 680
A Survey on the Memory Mechanism of Large Language Model based Agents
Zhang, Z., Bo, X., Ma, C., Li, R., Chen, X., Dai, Q., Zhu, J., Dong, Z., & Wen, J.-R. (2024) · arXiv · doi:10.48550/arxiv.2404.13501 · Cited by 149
A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation
Asgari, E., Montaña-Brown, N., Dubois, M., Khalil, S., Balloch, J., Yeung, J. A., & Pimenta, D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01670-7 · Cited by 423
Large Language Models for Mental Health Applications: Systematic Review
Guo, Z., Lai, A., Thygesen, J. H., Farrington, J., Keen, T., & Li, K. (2024) · JMIR Mental Health · doi:10.2196/57400 · Cited by 269
“Furthermore, hallucinations may stem from overfitting the training data or a lack of context understanding [134].”
BackgroundThe landscape of agentic reinforcement learning for LLMs: a survey
Zhang, G., Geng, H., Yu, X., Yin, Z., Zhang, Z., Tan, Z., Zhou, H., Li, Z., Xue, X., Li, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2509.02547 · Cited by 229
Self-citationWhat large language models know and what people think they know
Steyvers, M., Tejeda, H., Kumar, A., Belem, C., Karny, S., Hu, X., Mayer, L. W., & Smyth, P. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-024-00976-7 · Cited by 209
“One notable issue is the possibility of generating responses that, while convincing, may be inaccurate or nonsensical 9,10 .”
Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
Liu, F., Liu, Y., Shi, L., Yang, Z., Zhang, L., Lian, X., Li, Z., & Ma, Y. (2024) · arXiv · doi:10.48550/arxiv.2404.00971 · Cited by 188
Omar, M., Sorin, V., Collins, J. D., Reich, D., Freeman, R., Gavin, N., Charney, A., Stump, L., Bragazzi, N. L., Nadkarni, G. N., et al. (2025) · Communications Medicine · doi:10.1038/s43856-025-01021-3 · Cited by 204
From Matching to Generation: A Survey on Generative Information Retrieval
Li, X., Jin, J., Zhou, Y., Zhang, Y., Zhang, P., Zhu, Y., & Dou, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3722552 · Cited by 172
“Yet, these methods have their specific applicable scenarios, and more effective and universally applicable incremental learning strategies remain a key area for exploration.”
Hallucination is Inevitable: An Innate Limitation of Large Language Models
Xu, Z., Jain, S., & Kankanhalli, M. (2024) · arXiv · doi:10.48550/arxiv.2401.11817 · Cited by 180
“For an extensive review of hallucination in LLMs, readers are directed to recent surveys [24, 29, 37, 46, 66].”
BackgroundHallucination Mitigation for Retrieval-Augmented Large Language Models: A Review
Zhang, W., & Zhang, J. (2025) · Mathematics · doi:10.3390/math13050856 · Cited by 145
Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era
Dai, S., Chen, X., Xu, S., Pang, L., Dong, Z., & Xu, J. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671458 · Cited by 329
Long, S., Tan, J., Mao, B., Tang, F., Li, Y., Zhao, M., & Kato, N. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3526606 · Cited by 165
“Large models may produce varying results for the same prompt words or generate “hallucinations” on untrained data [199], [200].”
LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics
van Stein, B., & Bäck, T. (2024) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2024.3497793 · Cited by 183
“Since LLMs have been trained on an exceedingly large code base, including the currently available metaheuristics, we can explain their observed strong performance by interpreting them as a universal modular framework for algorithm construction (see also Section I) that have access to a huge number…”
Enhancing medical AI with retrieval-augmented generation: A mini narrative review
Gargari, O. K., & Habibi, G. (2025) · Digital Health · doi:10.1177/20552076251337177 · Cited by 178
Applications of LLMs for Generating Cyber Security Exercise Scenarios
Mudassar Yamin, M., Hashmi, E., Ullah, M., & Katt, B. (2024) · IEEE Access · doi:10.1109/access.2024.3468914 · Cited by 91
“For instance, LLMs can be used to generate imaginative and creative content, such as fiction, poetry, or art descriptions, pushing the boundaries of traditional human creativity [49], [50], [51].”
BackgroundTowards end-to-end automation of AI research
Lu, C., Lu, C., Lange, R. T., Yamada, Y., Hu, S., Foerster, J., Ha, D., & Clune, J. (2026) · Nature · doi:10.1038/s41586-026-10265-5 · Cited by 116
“However, some AI weaknesses have proved surprisingly difficult to solve, such as AI being easily fooled 41,42 and overconfidently wrong (hallucinations) 43 , although progress has been made 44,45 .”
Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective
Lavrinovics, E., Biswas, R., Bjerva, J., & Hose, K. (2024) · Journal of Web Semantics · doi:10.1016/j.websem.2024.100844 · Cited by 180
“Hallucinations are a multifaceted problem as there are conceptually di ff erent types such as hallucinations with respect to world knowledge, self-contradictions, with respect to prompt instructions or given context (Huang et al., 2023, Zhang et al., 2023), see Figure 1.”
Simulating Opinion Dynamics with Networks of LLM-based Agents
Chuang, Y.-S., Goyal, A., Harlalka, N., Suresh, S., Hawkins, R., Yang, S., Shah, D., Hu, J., & Rogers, T. (2024) · Findings of the Association for Computational Linguistics: NAACL 2024 · doi:10.18653/v1/2024.findings-naacl.211 · Cited by 85
Scientific evidence for clinical text summarization using large language models: scoping review
Bednarczyk, L., Reichenpfader, D., Gaudet-Blavignac, C., Ette, A. K., Zaghir, J., Zheng, Y., Bensahla, A., Bjelogrlic, M., & Lovis, C. (2025) · Journal of Medical Internet Research · doi:10.2196/68998 · Cited by 83
“While recent studies have attempted to establish taxonomies for hallucinations [79,80], failures may be inherently task-specific, underscoring the need for systematic error analysis and categorization based on existing research.”
Zhang, C., Xu, Q., Yu, Y., Zhou, G., Zeng, K., Chang, F., & Ding, K. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102883 · Cited by 124
UAVs meet LLMs: Overviews and perspectives towards agentic low-altitude mobility
Tian, Y., Lin, F., Li, Y., Zhang, T., Zhang, Q., Fu, X., Huang, J., Dai, X., Wang, Y., Tian, C., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103158 · Cited by 174
“). due to model hallucinations or inadequate task-specific adapt-ability [369, 370, 371].”
Qin, H. X., Jin, S., Gao, Z., Fan, M., & Hui, P. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642105 · Cited by 82
Calibrated Language Models Must Hallucinate
Kalai, A. T., & Vempala, S. S. (2024) · Proceedings of the 56th Annual ACM Symposium on Theory of Computing · doi:10.1145/3618260.3649777 · Cited by 91
Large language models for life cycle assessments: Opportunities, challenges, and risks
Preuss, N., Alshehri, A. S., & You, F. (2024) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2024.142824 · Cited by 71
Salih, S., Husain, O., Hamdan, M., Abdelsalam, S., Elshafie, H., & Motwakel, A. (2025) · Results in Engineering · doi:10.1016/j.rineng.2024.103837 · Cited by 74
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024) · arXiv · doi:10.48550/arxiv.2402.01680 · Cited by 1,713
Evaluating large language models and agents in healthcare: key challenges in clinical applications
Chen, X., Xiang, J., Lu, S., Liu, Y., He, M., & Shi, D. (2025) · Intelligent Medicine · doi:10.1016/j.imed.2025.03.002 · Cited by 136
A comprehensive survey on integrating large language models with knowledge-based methods
Yang, W., Some, L., Bain, M., & Kang, B. H. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113503 · Cited by 154
Introduction to Artificial Intelligence
Papajorgji, P. J., & Moskowitz, H. (2024) · Springer eBooks · doi:10.1007/978-3-031-78078-3_5 · Cited by 66
Wang, Y., Pan, Y., Su, Z., Deng, Y., Zhao, Q., Du, L., Luan, T. H., Kang, J., & Niyato, D. T. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3576176 · Cited by 147
“LM agents are susceptible to “hallucinations”, where their LMs generate outputs that are plausible but incorrect and not grounded in reality, potentially spreading misinformation in multi-agent environments [28].”
Han, S., Wang, M., Zhang, J., Li, D., & Duan, J. (2024) · Electronics · doi:10.3390/electronics13245040 · Cited by 103
Large Language Models in Medical Diagnostics: Scoping Review With Bibliometric Analysis
Su, H., Sun, Y., Li, R., Zhang, A., Yang, Y., Xiao, F., Duan, Z., Chen, J., Hu, Q., Yang, T., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/72062 · Cited by 79
“However, the hallucination problem in LLMs creates regulatory challenges for high-stakes applications [165].”
Can generative AI reliably synthesise literature? exploring hallucination issues in ChatGPT
Adel, A., & Saleem, N. H. (2025) · AI & Society · doi:10.1007/s00146-025-02406-7 · Cited by 80
A survey on state-of-the-art deep learning applications and challenges
Noor, M. H. M., & Ige, A. O. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111225 · Cited by 120
Dikmen, İ., Eken, G., Erol, H., & Birgönül, M. T. (2025) · Computers in Industry · doi:10.1016/j.compind.2025.104251 · Cited by 80
“Direct application of LLMs to process construction contracts may even lead to unprofessional incorrect outputs due to hallucination (Huang et al., 2023).”
Xu, Q., Qiu, F., Zhou, G., Zhang, C., Ding, K., Chang, F., Lu, F., Yu, Y., Ma, D., & Liu, J. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103244 · Cited by 71
Fang, L., Yu, X., Cai, J., Chen, Y., Wu, S., Liu, Z., Yang, Z., Lu, H., Gong, X., Liu, Y., et al. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11423-3 · Cited by 124
Self-citationTozuka, R., Johno, H., Amakawa, A., Sato, J., Muto, M., Seki, S., Komaba, A., & Onishi, H. (2024) · Japanese Journal of Radiology · doi:10.1007/s11604-024-01705-1 · Cited by 79
“This phenomenon, referred to as LLM hallucinations, can generate seemingly plausible but factually incorrect information, making it difficult to rely on LLMs for clinical diagnoses [2, 5, 6].”
Developing ChemDFM as a large language foundation model for chemistry
Zhao, Z., Ma, D., Chen, L., Sun, L., Li, Z., Xia, Y., Chen, B., Xu, H., Zhu, Z., Su, Z., et al. (2025) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2025.102523 · Cited by 194
When Large Language Models Meet Vector Databases: A Survey
Jing, Z., Su, Y., & Han, Y. (2025) · 2025 Conference on Artificial Intelligence x Multimedia (AIxMM) · doi:10.1109/aixmm62960.2025.00008 · Cited by 93
“LLMs often generate plausible yet factually incorrect or nonsensical information [5].”
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
Abootorabi, M. M., Zobeiri, A., Dehghani, M., Mohammadkhani, M., Mohammadi, B., Ghahroodi, O., Baghshah, M. S., & Asgari, E. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.861 · Cited by 76
Artificial intelligence in medical education: promise, pitfalls, and practical pathways
Saroha, S. (2025) · Advances in Medical Education and Practice · doi:10.2147/amep.s523255 · Cited by 53
“42 Furthermore, as with discharge summaries once typed by hospital transcriptionists, AI-generated notes require careful proofreading and verification.”
Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey
Liu, X., Chen, T., Da, L., Chen, C., Lin, Z., & Wei, H. (2025) · Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · doi:10.1145/3711896.3736569 · Cited by 53
Applications of multimodal large language models in construction industry
Erfani, A., & Mansouri, A. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103909 · Cited by 61
Large language models provide unsafe answers to patient-posed medical questions
Draelos, R. L., Afreen, S., Blasko, B., Brazile, T. L., Chase, N., Desai, D. P., Evert, J., Gardner, H. L., Herrmann, L., House, A. V., et al. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02428-5 · Cited by 87
KoSEL: Knowledge subgraph enhanced large language model for medical question answering
Zeng, Z., Cheng, Q., Hu, X., Zhuang, Y., Liu, X., He, K., & Liu, Z. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112837 · Cited by 60
Chen, J., & Bao, Y. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106331 · Cited by 60
Evaluating large language model agents for automation of atomic force microscopy
Mandal, I., Soni, J., Zaki, M. F. M., Smedskjær, M. M., Wondraczek, K., Wondraczek, L., Gosvami, N. N., & Krishnan, N. M. A. (2025) · Nature Communications · doi:10.1038/s41467-025-64105-7 · Cited by 98
“Rather tool coordination capabilities of LLMs prove to be an important aspect for effective agentic implementation.”
InfluentialGenerative AI and Large Language Models - Benefits, Drawbacks, Future and Recommendations
Håkansson, A., & Phillips-Wren, G. E. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.689 · Cited by 52
Xu, H., Zhang, N., Yin, Z., & Njock, P. G. A. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106257 · Cited by 50
Language-driven Grasp Detection
Vuong, A. D., Vu, M. N., Huang, B., Nguyen, N., Le, H., Vo, T., & Nguyen, A. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01695 · Cited by 39
Exploring accounting and AI using topic modelling
Murphy, B., Feeney, O., Rosati, P., & Lynn, T. (2024) · International Journal of Accounting Information Systems · doi:10.1016/j.accinf.2024.100709 · Cited by 87
Human Factors Requirements for Human-AI Teaming in Aviation
Kirwan, B. (2025) · Future Transportation · doi:10.3390/futuretransp5020042 · Cited by 66
Large scale foundation models for intelligent manufacturing applications: a survey
Zhang, H., Semujju, S. D., Wang, Z., Lv, X., Xu, K., Wu, L., Jia, Y., Wu, J., Liang, W., Zhuang, R., et al. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02536-7 · Cited by 82
When IoT Meet LLMs: Applications and Challenges
Kök, İ., Demirci, O., & Özdemir, S. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825187 · Cited by 73
“This data helps mitigate a critical challenge in LLMs—hallucination, where models generate contextually or physically implausible outputs [5].”
AI in microbiome‐related healthcare
Probul, N., Huang, Z., Saak, C. C., Baumbach, J., & List, M. (2024) · Microbial Biotechnology · doi:10.1111/1751-7915.70027 · Cited by 36
Guo, J., Wang, M., Yin, H., Song, B., Chi, Y., Yu, F. R., & Yuen, C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3496491 · Cited by 51
“2) Model Hallucination Phenomenon: Model hallucinations [176] can be categorized into factuality and faithfulness hallucinations.”
BackgroundLearning to break: Knowledge-enhanced reasoning in multi-agent debate system
Wang, H., Du, X., Yu, W., Chen, Q., Zhu, K., Chu, Z., Yan, L., & Guan, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2024.129063 · Cited by 36
Self-citationAgentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Singh, A., Ehtesham, A., Kumar, S., Khoei, T. T., & Vasilakos, A. V. (2025) · arXiv · doi:10.48550/arxiv.2501.09136 · Cited by 36
On large language models safety, security, and privacy: A survey
Zhang, R., Li, H., Qian, X., Jiang, W., & Chen, H.-X. (2025) · Journal of Electronic Science and Technology · doi:10.1016/j.jnlest.2025.100301 · Cited by 65
Huang, G. I., Wong, I. A., Zhang, C., & Liang, Q. (2025) · International Journal of Hospitality Management · doi:10.1016/j.ijhm.2025.104112 · Cited by 51
LEGO-GraphRAG: Modularizing Graph-Based Retrieval-Augmented Generation for Design Space Exploration
Cao, Y., Gao, Z., Li, Z., Xie, X., Zhou, S. K., & Xu, J. (2025) · Proceedings of the VLDB Endowment · doi:10.14778/3748191.3748194 · Cited by 35
Linardon, J., Jarman, H. K., McClure, Z., Anderson, C., Liu, C., & Messer, M. (2025) · JMIR Mental Health · doi:10.2196/80371 · Cited by 40
“These concerns are not unfounded, as one of the most well-documented limitations of LLMs is their tendency to “hallucinate,” which occurs when the model generates false, fabricated, or unverifiable information that appears coherent and credible [6].”
Thanasi-Boçe, M., & Hoxha, J. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-12775-z · Cited by 46
When Fuzzing Meets LLMs: Challenges and Opportunities
Jiang, Y., Liang, J., Ma, F., Chen, Y., Zhou, C., Shen, Y., Wu, Z., Fu, J., Wang, M., Li, S., et al. (2024) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3663529.3663784 · Cited by 75
Zhuang, Y., Yu, L.-C., Jiang, N., & Ge, Y. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109887 · Cited by 42
Large language models for automated scholarly paper review: A survey
Zhuang, Z., Chen, J., Xu, H., Jiang, Y., & Lin, J. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103332 · Cited by 34
“The issue of hallucinations (Xu et al., 2024; Huang et al., 2025) in LLMs has been a persistent challenge since their inception, stemming from the inherent complexities of the generation mechanisms.”
Kenthapadi, K., Sameki, M., & Taly, A. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671467 · Cited by 36
Hallucination to truth: a review of fact-checking and factuality evaluation in large language models
Rahman, S. S., Islam, M. A., Alam, M. M., Zeba, M., Rahman, M. A., Chowa, S. S., Raiaan, M. A. K., & Azam, S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11454-w · Cited by 39
“In contrast, extrinsic hallucinations introduce information that cannot be verified by any provided evidence, resulting in output unsupported by the source and often containing fabricated details [50, 60, 63].”
InfluentialLanguage models for materials discovery and sustainability: Progress, challenges, and opportunities
Pei, Z., Yin, J., & Zhang, J. (2025) · Progress in Materials Science · doi:10.1016/j.pmatsci.2025.101495 · Cited by 30
Miedema, E., Waschull, S., & Emmanouilidis, C. (2025) · Computers in Industry · doi:10.1016/j.compind.2025.104409 · Cited by 46
Song, Y., Cui, M., Wan, F., Yu, Z., & Jiang, J. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2025.2483858 · Cited by 30
“…scenarios through various theoretical frameworks, such as technology acceptance theory (Christensen et al., 2025) and improvisation theory (Huang et al., 2025), this research employs the conservation of resources framework to analyze the impact mechanism of AI hallucination on user AI…”
InfluentialSteenstra, I., Nouraei, F., & Bickmore, T. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714014 · Cited by 61
Galli, C., Gavrilova, A. V., & Calciolari, E. (2025) · Information · doi:10.3390/info16050378 · Cited by 36
Robson, M. J., Xu, S., Wang, Z., Chen, Q., & Francesco Ciucci, A. (2025) · Advanced Materials · doi:10.1002/adma.202502649 · Cited by 32
Self-citationLLM Guided Evolution - The Automation of Models Advancing Models
Morris, C., Jurado, M., & Zutty, J. (2024) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3638529.3654178 · Cited by 58
Conformal Prediction for Natural Language Processing: A Survey
Campos, M., Farinhas, A., Zerva, C., Figueiredo, M. A. T., & Martins, A. F. T. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00715 · Cited by 124
Multi-modal large language models in radiology: principles, applications, and potential
Shen, Y., Xu, Y., Ma, J., Rui, W., Zhao, C., Heacock, L. C., & Huang, C. (2024) · Abdominal Radiology · doi:10.1007/s00261-024-04708-8 · Cited by 40
“This occurs because LLMs and MLLMs often prioritize the plausibility of generated content over factuality [120] .”
Luo, S. X., Chen, W., Tian, W., Liu, R., Hou, L., Zhang, X., Shen, H., Wu, R., Geng, S., Zhou, Y., et al. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3406372 · Cited by 63
“Despite the robust reasoning capability of LLMs, LLM-based autonomous systems are still vulnerable to some intricate cases such as a really rare object in the picture, poor feature quality due to the perception sensors, or intrinsic hallucination problem [73].”
BackgroundRiaz, I. B., Naqvi, S. A. A., Hasan, B., & Murad, M. H. (2024) · Mayo Clinic Proceedings Digital Health · doi:10.1016/j.mcpdig.2024.05.023 · Cited by 31
“28 This phenomenon can lead to the generation of inaccurate or misleading content.”
Mostafa, M. A., Almogren, A., Al‐Qurishi, M., & Alrubaian, M. (2024) · ACM Computing Surveys · doi:10.1145/3700748 · Cited by 44
DD-Aug: A Knowledge-to-Image Synthetic Data Augmentation Pipeline for Industrial Defect Detection
Ren, W., Song, K., Chen, C.-Y., Chen, Y., Hong, J., Fan, M., Ouyang, X., Zhu, Y., & Xiao, J. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3495786 · Cited by 32
“Huang et al. [21] pointed out that large models can exhibit fact-conflicting hallucinations, producing outputs that contradict known facts, potentially misleading users who may not be well versed in the subject matter.”
Artificial intelligence for drug delivery: Yesterday, today and tomorrow
Wu, Y., Wang, N., Xiong, P., Wang, R., Deng, J., & Ouyang, D. (2025) · Acta Pharmaceutica Sinica B · doi:10.1016/j.apsb.2025.09.022 · Cited by 39
Hallucination Detection in Large Language Models with Metamorphic Relations
Yang, B., Mamun, M. A. A., Zhang, J. M., & Uddin, G. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3715735 · Cited by 67
Qi, L., Xie, J., Hu, C., Xu, X., Xiang, H., Dai, H., Gu, R., Zhang, X., & Dou, W. (2025) · ACM Transactions on Information Systems · doi:10.1145/3771772 · Cited by 36
Fayyazi, R., Taghdimi, R., & Yang, S. J. (2024) · Annual Computer Security Applications Conference Workshops (ACSAC Workshops) · doi:10.1109/acsacw65225.2024.00036 · Cited by 45
“Despite the proficiency of d-LLMs in instruction-following tasks (e.g., question-answering), these models have shown to be prone to hallucination in their generated responses [13], [14].”
Nishisako, S., Higashi, T., & Wakao, F. (2025) · JMIR Cancer · doi:10.2196/70176 · Cited by 40
“A major issue with generative AI responses is their potential to provide incorrect yet seemingly plausible information, known as hallucination [22,23].”
Object detection with multimodal large vision-language models: An in-depth review
Sapkota, R., & Karkee, M. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103575 · Cited by 69
“…[160,288,289], open-vocabulary expansion using weak supervision [290,291], and knowledge graph grounding [292,293] Expands LVLM coverage to rare or newly introduced object classes [160]; Reduces retraining needs when new categories are added [103,129] Information Fusion 126 (2026) 103575 [300,301].”
One-for-More: Continual Diffusion Model for Anomaly Detection
Li, X., Tan, X., Chen, Z., Zhang, Z., Zhang, R.-X., Guo, R., Jiang, G., Chen, Y., Qu, Y., Ma, L., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00449 · Cited by 62
“Furthermore, as shown in Figure 1 (bottom), the ControlNet [47], after training in the latest class, suffers from “faithfulness hallucina-tion” [16].”
Technological folie à deux: Feedback Loops Between AI Chatbots and Mental Illness
Dohnány, S., Kurth-Nelson, Z., Spens, E., Luettgau, L., Reid, A., Gabriel, I., Summerfield, C., Shanahan, M., & Nour, M. M. (2025) · arXiv · doi:10.48550/arxiv.2507.19218 · Cited by 26
Fayyazi, R., Taghdimi, R., & Yang, S. J. (2024) · arXiv · doi:10.48550/arxiv.2401.00280 · Cited by 25
Stephan, D., Bertsch, A., Schumacher, S., Puladi, B., Burwinkel, M., Al‐Nawas, B., Kämmerer, P. W., & Thiem, D. G. E. (2025) · Journal of Medical Internet Research · doi:10.2196/73337 · Cited by 43
Karim, M. M., Shi, Y., Zhang, S., Wang, B., Nasri, M., & Wang, Y. (2025) · Artificial Intelligence for Transportation · doi:10.1016/j.ait.2025.100004 · Cited by 48
Combining Multiple Large Language Models Improves Diagnostic Accuracy
Barabucci, G., Shia, V., Chu, E., Harack, B., Laskowski, K., & Fu, N. (2024) · NEJM AI · doi:10.1056/aics2400502 · Cited by 24
Luo, M., Fei, H., Li, B., Wu, S., Liu, Q., Poria, S., Cambria, E., Lee, M. L., & Hsu, W. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680705 · Cited by 38
Knowledge assimilation: Implementing knowledge-guided agricultural large language model
Jiang, J., Yan, L., Liu, H., Xia, Z., Wang, H., Yang, Y., & Guan, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113197 · Cited by 37
Self-citationWithers, C. A., Rufai, A. M., Venkatesan, A., Tirunagari, S., Lobentanzer, S., Harrison, M., & Zdrazil, B. (2025) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2025.2490835 · Cited by 40
“Several factors contribute to hallucinations, one of the primary ones being a model’s limited knowledge or insufficient context for a specific task [90].”
Guo, K., Wong, P. K.-Y., Cheng, J. C. P., Chan, C.-F., Leung, P.-H., & Tao, X. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106490 · Cited by 57
The trust crisis in artificial intelligence: AI hallucinations and human-AI collaboration
Cheng, Q., Dai, Y., Liu, X., & Peng, S. (2026) · Technology in Society · doi:10.1016/j.techsoc.2026.103286 · Cited by 34
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.