A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
Open accessThe DOI matches its Crossref record; 496 of the 496 references it cites were found in a registry or an index; 110 of the 234 sources its claims cite were checked for support.
Abstract
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content. This phenomenon raises significant concerns over the reliability of LLMs in real-world information retrieval (IR) systems and has attracted intensive research to detect and mitigate such hallucinations. Given the open-ended general-purpose attributes inherent to LLMs, LLM hallucinations present distinct challenges that diverge from prior task-specific models. This divergence highlights the urgency for a nuanced understanding and comprehensive overview of recent advances in LLM hallucinations. In this survey, we begin with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, we present a thorough overview of hallucination detection methods and benchmarks. Our discussion then transfers to representative methodologies for mitigating LLM hallucinations. Additionally, we delve into the current limitations faced by retrieval-augmented LLMs in combating hallucinations, offering insights for developing more robust IR systems. Finally, we highlight the promising research directions on LLM hallucinations, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.
Overview
CoChat Summary
TL;DR
This survey proposes a taxonomy of LLM hallucination into factuality and faithfulness, then reviews causes, detection methods, benchmarks, mitigation strategies, and RAG-specific challenges. It also outlines open directions including hallucinations in large vision-language models and understanding knowledge boundaries in LLMs.
Key findings
- Redefines LLM hallucination as factuality hallucination (factual contradiction: entity-error, relation-error; factual fabrication: unverifiability, overclaim) and faithfulness hallucination (instruction inconsistency, context inconsistency, logical inconsistency).
- Identifies causes across data (misinformation/biases, knowledge boundary, inferior alignment data), training (pre-training, SFT, RLHF), and inference (imperfect decoding, over-confidence, softmax bottleneck, reasoning failure).
- Reviews detection and benchmarks: factuality detection via fact-checking and uncertainty estimation; faithfulness detection via fact-based, classifier-based, QA-based, uncertainty-based, and LLM-based metrics. Reported benchmark sizes include TruthfulQA (817 questions), HaluEval (30,000 task-specific and 5,000 general samples), FreshQA (600 hand-crafted questions), and HaluEval 2.0 (8,770 questions across five domains).
- Mitigation is organized by cause: data filtering, model editing, RAG; pre-training/alignment fixes; and factuality/faithfulness enhanced decoding. RAG still faces retrieval failure and generation bottleneck.
Methods
- Design: a survey/overview that proposes a taxonomy and organizes literature on LLM hallucination principles, causes, detection, benchmarks, mitigation, RAG challenges, and future directions.
- Data or sample: no primary dataset or new experiments; synthesizes existing research and benchmarks such as TruthfulQA, HaluEval, FreshQA, and HaluEval 2.0.
- Main analysis: conceptual categorization and qualitative synthesis; no quantitative meta-analysis is reported.
Limitations
- The paper does not explicitly state limitations of the survey itself.
- It states limitations of reviewed methods: RAG can be impacted by irrelevant retrievals and shallow retriever-generator interactions; fact-checking solely via LLM parametric knowledge may yield inaccurate assessments; classifier-based faithfulness metrics are constrained by scarcity of annotated data.
- Text makes evident: as a survey, it presents no original empirical validation or new benchmark results.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
76 Valid · 5 Not valid · 48 Not checked · 108 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Recent studies have highlighted a strong correlation between the model's accuracy on general domain questions and the volume of relevant documents [145] or entity popularity [204] within the pre-training corpora.”
What the sources say
- Supportedcites [145] [145] Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, and Colin Raffel. 2023. Large Language Models Struggle to Learn Long-Tail Knowledge. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202) , Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 15696-15707. https: //proceedings.mlr.press/v202/kandpal23a.html - source
The citation to this paper is attached to the volume of relevant documents, not the separate entity-popularity claim. Section 3.1 (p. 5) reports a strong correlation between question-answering accuracy and relevant pre-training document count across the tested models. (LLM, conf=0.94)
- Partly supportedcites [204] [204] Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023 , Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Computational Linguistics, 9802-9822. https://doi.org/10.18653/v1/2023.acl-long.546 - sourceExperimental — accuracy not yet measured
The “Subject entity popularity predicts memorization” section reports a positive correlation between entity popularity and question-answering accuracy for almost all relationship types. However, the paper measures popularity using Wikipedia page views as a proxy, not entity frequency within pre-training corpora. Its Limitations section also says the experiments rely on synthetic datasets and that applicability to naturally occurring questions is not firmly established. (LLM, conf=0.87)
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Such biases can be inadvertently acquired from internet-based texts, which are rife with diverse and biased viewpoints, and subsequently be propagated into the generated content [155].”
What the sources say
- Partly supportedcites [155] [155] Faisal Ladhak, Esin Durmus, Mirac Suzgun, Tianyi Zhang, Dan Jurafsky, Kathleen McKeown, and Tatsunori Hashimoto. 2023. When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics . Association for Computational Linguistics, Dubrovnik, Croatia, 3206-3219. https://aclanthology.org/2023.eacl-main.234 - sourceExperimental — accuracy not yet measured
The Abstract and §6 Discussion report that pre-training biases can propagate into generated summaries as hallucinated facts. But §6 leaves the source of those biases for future work and treats stereotyping in pre-training data as one possibility; it does not establish that they were acquired from internet-based texts. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Neural networks possess an intrinsic tendency to memorize training data [35]”
What the sources say
- Partly supportedcites [35] [35] Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21) . 2633-2650. - sourceExperimental — accuracy not yet measured
Section 3.1 (p. 3) says memorization is in many ways an essential component of language models, and the Introduction (p. 1) demonstrates that large language models memorize individual training examples. The claim extends that finding to neural networks generally; the cited passages do not establish an intrinsic tendency across all neural networks. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, certain biases are intrinsically tied to hallucinations, especially those related to gender [242] and nationality [155, 226].”
What the sources say
- Not matchedcites [242]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [155] [155] Faisal Ladhak, Esin Durmus, Mirac Suzgun, Tianyi Zhang, Dan Jurafsky, Kathleen McKeown, and Tatsunori Hashimoto. 2023. When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics . Association for Computational Linguistics, Dubrovnik, Croatia, 3206-3219. https://aclanthology.org/2023.eacl-main.234 - source
The Introduction and Section 3.3 report a strong association between pre-trained models’ name–nationality bias and nationality hallucinations in downstream text summarization. The citation to this paper is attached to nationality; the separate gender citation is not assessed here. (LLM, conf=0.89)
- Not matchedcites [226]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
Every source the paper cites for this claim was checked and supports it.
In the paper
“this memorization tendency grows with model size [34, 54]”
What the sources say
- Supportedcites [34] [34] Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. 2022. Quantifying memorization across neural language models. ArXiv preprint abs/2202.07646 (2022). https://arxiv.org/ abs/2202.07646 - source
Section 4.1 (p. 4) reports that larger models memorize significantly more than smaller models. The Introduction (p. 2) specifies that this finding is within model families, and the Conclusion (p. 9) describes memorization as scaling with model size. (LLM, conf=0.94)
- Supportedcites [54] [54] Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, H source
Section 7, “Memorization” (p. 35), explicitly concludes that larger models have a higher memorization rate than smaller models. It also reports that the exact-continuation match rate rises from 1.6% for the 8B model to 2.4% for the 540B model. (LLM, conf=0.94)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
102 more claims · 41 with their cited sources checked
Create a free account to see all 237 claims and to verify the 13 references still open.
- Probably not a substantial claim. 97
- It may state two separate claims as one. 55
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, LLMs exhibit hallucination and fabrication errors that are unacceptable for quantitative modeling [19, 20, 21].”
From Structured Schemas for Provenance‐Rich, LLM ‐Assisted QSP Model Calibration (2026) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In particular, the generation of non-existent academic references or legal precedents has been widely recognized as a critical issue [4].”
From Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy (2025) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Retrieval augmentation, tool use, citation systems, constrained decoding, domain-specific training, and multimodal grounding can all supply partial external anchoring, and they alter both the frequency and the detectability of unsupported claims [15,29].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [15]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These measures do reduce the frequency of unsupported claims and improve the odds that a learner can detect one, and the argument here does not depend on denying it [15,29].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [15]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents.It does not check whether retrieved evidence is attributed to the correct entity.”
From Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation (2026) · cites this paper as Huang et al., 2025
Experimental — accuracy not yet measured
21 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2.3 Hallucinations in Large Language Models · p. 7
“the final answer of x=4 is inconsistent with the reasoning chain, leading to an incorrect result.”
§ 2.3 Hallucinations in Large Language Models · p. 6
“Step 2: Divide both sides by 2 to get: x = 3. So the result of the equation is x=3.”
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 1×
“To align with human preferences, RLHF optimizes the LLM to generate outputs that maximize the reward provided by the trained preference model, typically employing a reinforcement learning algorithm, such as Proximal Policy Optimization (PPO)(Schulman et al., 2017).”
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“While scaling up pre-training data substantially enhances the competencies of LLMs (Kaplan et al., 2020; Hoffmann et al., 2022), challenges arise in maintaining consistent data quality, which can potentially introduce misinformation and biases (Bender et al., 2021; Weidinger et al., 2021).”
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · cited 10×
“By retrieving evidence from external knowledge bases, RAG enables LLMs to be equipped with up-to-date knowledge and generate responses conditioning on relevant evidence.”
InfluentialLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(2017) · doi:10.1109/cvpr35066.2017 · Cited by 7,141
Research works printed but not linked: 33
- ArXiv. 2023. arxiv dataset. Retrieved from https://www.kaggle.com/datasets/Cornell-University/arxiv/versions/134
- Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled sampling for sequence prediction with recurrent neural networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems. Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.), 1171–1179. Retrieved from https://proceedings.neurips.cc/paper/2015/hash/e995f98d56967d946471af29d7bf99f1-Abstract.html
- Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from trillions of tokens. In Proceedings of theInternational Conference on Machine Learning (ICML ’22). Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato (Eds.), Proceedings of Machine Learning Research, Vol. 162, PMLR, 2206–2240. Retrieved from https://proceedings.mlr.press/v162/borgeaud22a.html
- 10.5555/3495724.3495883 · doi:10.5555/3495724.3495883
- 10.5555/3600270.3602050 · doi:10.5555/3600270.3602050
- Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. In Proceedings of the 31st International Conference on Neural Information Processing Systems. Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.), 4299–4307. Retrieved from https://proceedings.neurips.cc/paper/2017/hash/d5e2c0adad503c91f91df240d0cd4e49-Abstract.html
- Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and play language models: A simple approach to controlled text generation. In Proceedings of the 8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=H1edEyBKDS
- Bikash Gyawali, Lucas Anastasiou, and Petr Knoth. 2020. Deduplication of scholarly documents using locality sensitive hashing and word embeddings. In Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association, 901–910. Retrieved from https://aclanthology.org/2020.lrec-1.113
- Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The curious case of neural text degeneration. In Proceedings of the 8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=rygGQyrFvH
- Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie Zhou, Wenge Rong, and Zhang Xiong. 2023d. Transformer-Patcher: One mistake worth one neuron. In Proceedings of the 11th International Conference on Learning Representations (ICLR ’23). OpenReview.net. Retrieved from https://openreview.net/pdf?id=4oYUGeGBPm
- Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2022. Unsupervised dense information retrieval with contrastive learning. Transactions on Machine Learning Research 2022 (2022). Retrieved from https://openreview.net/forum?id=jKN1pXi7b0
- Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, and Colin Raffel. 2023. Large language models struggle to learn long-tail knowledge. In Proceedings of the International Conference on Machine Learning (ICML ’23). Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.), Proceedings of Machine Learning Research, Vol. 202, PMLR, 15696–15707. Retrieved from https://proceedings.mlr.press/v202/kandpal23a.html
- Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2020. Generalization through memorization: Nearest neighbor language models. In Proceedings of the 8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=HklBjCEKvH
- 10.5555/3600270.3601883 · doi:10.5555/3600270.3601883
- Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proceedings of the 31st International Conference on Neural Information Processing Systems. Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.), 6402–6413. Retrieved from https://proceedings.neurips.cc/paper/2017/hash/9ef2ed4b7fd2c810847ffa5fa85bce38-Abstract.html
- 10.5555/3600270.3602776 · doi:10.5555/3600270.3602776
- 10.5555/3495724.3496517 · doi:10.5555/3495724.3496517
- Jinming Li, Wentao Zhang, Tian Wang, Guanglei Xiong, Alan Lu, and Gerard Medioni. 2023. GPT4Rec: A generative framework for personalized recommendation and user interests interpretation. In Proceedings of the SIGIR Workshop on eCommerce Co-located with the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 23). Surya Kallumadi, Yubin Kim, Tracy Holloway King, Shervin Malmasi, Maarten de Rijke, and Jacopo Tagliabue (Eds.), CEUR Workshop Proceedings, Vol. 3589, CEUR-WS.org. Retrieved from https://ceur-ws.org/Vol-3589/paper_2.pdf
- Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out. Association for Computational Linguistics, 74–81. Retrieved from https://aclanthology.org/W04-1013
- 10.5555/3600270.3601532 · doi:10.5555/3600270.3601532
- Kevin Meng, Arnab Sen Sharma, Alex J. Andonian, Yonatan Belinkov, and David Bau. 2023. Mass-editing memory in a transformer. In Proceedings of the 11th International Conference on Learning Representations (ICLR ’23). OpenReview.net. Retrieved from https://openreview.net/pdf?id=MkbcAHIYgyS
- Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D. Manning. 2022. Fast model editing at scale. In Proceedings of the 10th International Conference on Learning Representations (ICLR ’22). OpenReview.net. Retrieved from https://openreview.net/forum?id=0DcZxeWfOPt
- Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. In NeurIPS. Retrieved from http://papers.nips.cc/paper_files/paper/2022/hash/b1efde53be364a73914f58805a001731-Abstract-Conference.html
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.
- Anton Sinitsin, Vsevolod Plokhotnyuk, Dmitriy Pyrkin, Sergei Popov, and Artem Babenko. 2020. Editable neural networks. In Proceedings of the8th International Conference on Learning Representations (ICLR ’20). OpenReview.net. Retrieved from https://openreview.net/forum?id=HJedXaEtvS
- 10.5555/3495724.3495977 · doi:10.5555/3495724.3495977
- Chenmien Tan, Ge Zhang, and Jie Fu. 2024. Massive editing for large language model via meta learning. In Proceedings of the 12th International Conference on Learning Representations. Retrieved from https://openreview.net/forum?id=L6L1CJQ2PE
- Zirui Wang Jiahui Yu Adams Wei Yu Zihang Dai Yulia Tsvetkov and Yuan Cao. 2022. SimVLM: Simple visual language model pretraining with weak supervision. In Proceedings of the 10th International Conference on Learning Representations (ICLR ’22). OpenReview.net. Retrieved from https://openreview.net/forum?id=GUrhfTuf_3
- 10.5555/3600270.3602070 · doi:10.5555/3600270.3602070
- Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov, and William W. Cohen. 2018. Breaking the softmax bottleneck: A high-rank RNN language model. In Proceedings of the6th International Conference on Learning Representations (ICLR ’18). OpenReview.net. Retrieved from https://openreview.net/forum?id=HkwZSG-CZ
- Zhilin Yang, Thang Luong, Ruslan Salakhutdinov, and Quoc V. Le. 2019. Mixtape: Breaking the softmax bottleneck efficiently. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS ’19). Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett (Eds.), 15922–15930. Retrieved from https://proceedings.neurips.cc/paper/2019/hash/512fc3c5227f637e41437c999a2d3169-Abstract.html
- Weizhe Yuan, Graham Neubig, and Pengfei Liu. 2021. BARTScore: Evaluating generated text as text generation. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS ’21). Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.), 27263–27277. Retrieved from https://proceedings.neurips.cc/paper/2021/hash/e4d2b6e6fdeca3e60e0f1a62fee3d9dd-Abstract.html
- Hugh Zhang, Daniel Duckworth, Daphne Ippolito, and Arvind Neelakantan. 2021. Trading off diversity and quality in natural language generation. In Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval). Association for Computational Linguistics, 25–33. Retrieved from https://aclanthology.org/2021.humeval-1.3
Cited by
Items 401–500 of 2,245
Bodaghi, A., Fung, B. C. M., & Schmitt, K. (2024) · ACM Transactions on the Web · doi:10.1145/3700791 · Cited by 12
Investigating Users' Search Behavior and Outcome with ChatGPT in Learning-oriented Search Tasks
Liu, S., Hu, Y., Tian, Z., Jin, Z., Ruan, S., & Mao, J. (2024) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3673791.3698406 · Cited by 14
Zhang, T., Ren, Y., Hou, C., et al. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10821952 · Cited by 5
“This process can be viewed as a basic application of Retrieval Augmented Generation (RAG), a technology designed to mitigate the problem of hallucination in LLM [27].”
BackgroundGórski, Ł., & Ramakrishna, S. (2025) · IT Professional · doi:10.1109/mitp.2024.3518917 · Cited by 5
“To address this, several hallucination detection and mitigation techniques have been proposed, 12 including entailment-based approaches, chain of verification, simple cosine-based methods, and multiple Q&A pair approaches.”
Gün, M., & Aktaş, Y. (2025) · American Journal of Hospice and Palliative Medicine® · doi:10.1177/10499091251352100 · Cited by 8
“21,22 Although arti fi cial intelligence offers substantial bene fi ts in clinical work fl ows, its expanding use is likely to raise new ethical questions.”
A Layered Multi-Expert Framework for Long-Context Mental Health Assessments
Tang, J., Guo, Q., Sun, W., & Shang, Y. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00080 · Cited by 5
“Second, long and complex transcripts —such as multi-turn interviews or narrative case studies—can overwhelm advanced models, leading to hallucinations or inconsistencies [6], [7].”
Higashi, K., Nakagawa, Z., Yamada, T., & Mori, H. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.10.26.620145 · Cited by 8
“The strategic limitation of LLM usage to specific, critical tasks mitigated the risk of hallucinations – a common concern with LLMs[41,42].”
BackgroundThe AI Agent in the Room: Informing Objective Decision Making at the Transplant Selection CommitteePreprint
Hasjim, B. J., Azarfar, G., Lee, F. G., et al. (2024) · medRxiv · doi:10.1101/2024.12.06.24318575 · Cited by 5
“28,29 Redundant variables (e.g., history of diabetes vs. insulin dependence) and those with >20% missing data were excluded 30,31 to minimize hallucinations.”
Retrieval-Augmented Text Generation: Methods, Challenges, and ApplicationsPreprint
Genesis, J. (2025) · Preprints.org · doi:10.20944/preprints202504.0443.v1 · Cited by 17
Neuro-symbolic LLM Integration in Clinical Medicine: A Systematic Review and TaxonomyPreprint
Gorenshtein, A., Omar, M., Barash, Y., Nadkarni, G. N., & Klang, E. (2026) · Research Square · doi:10.21203/rs.3.rs-8902022/v1 · Cited by 4
“39,40 Systems that treat symbolic components as optional context can still fail silently, because the LLM remains free to interpolate beyond retrieved facts.”
Gilani, K., Verket, M., Peters, C., Dumontier, M., Rocca, H.-P. B.-L., & Urovi, V. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110745 · Cited by 5
Vakharia, P., Kufeldt, A., Meyers, M., Lane, I., & Gilpin, L. H. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-71170-1_23 · Cited by 5
“As for their cause, hallucinations can originate in any part of the language modeling process, from data to the inference step [7][4].”
BackgroundFactualRAG: a RAG-Powered framework for LLM fact-checking via IFCN-Accredited sources
Chang, L.-J., & Lai, C.-M. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-026-01041-y · Cited by 5
“…recent analyses highlight that LLM-based verification sys - tems remain vulnerable to subtle manipulation, adversarial framing, and domain-specific biases, raising concerns about their reliability in real-world misinformation scenarios (Chen & Shu, 2024; Huang et al., 2025a; Rony et al., 2024 ).”
Li, Y., Fu, X., Verma, G., Buitelaar, P., & Liu, M. (2025) · arXiv · doi:10.48550/arxiv.2510.24476 · Cited by 4
Inferring Drug–Gene Relationships in Cancer Using Literature-Augmented Large Language Models
Lai, Y.-J., Wang, L.-J., Yasaka, T. M., Shin, Y., Ning, M., Tan, Y., Shih, C.-H., Guo, Y., Chen, P.-Y., Galloway, H., et al. (2025) · Cancer Research Communications · doi:10.1158/2767-9764.crc-25-0030 · Cited by 4
A comparison of conversational chatbots and the internet for consumer information search
Tafesse, W., & Mamo, Y. (2025) · Behaviour and Information Technology · doi:10.1080/0144929x.2025.2517215 · Cited by 6
“Biases can also be introduced during the reinforcement learning phase, when model developers attempt to align their models to particular worldviews (Huang et al. 2025).”
GAL-KARS: Exploiting LLMs for Graph Augmentation in Knowledge-Aware Recommender Systems
Spillo, G., Musto, C., Mannavola, M., de Gemmis, M., Lops, P., & Semeraro, G. M. (2025) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3699682.3728342 · Cited by 7
iAMeta: Advancing multimodal metaphor detection using MLLMs and information debiasing
He, X., Yu, L., & Tian, S. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103348 · Cited by 6
Belief in neuromyths among primary school teachers: A cross-national study of 11 countries
Adıgüzel, O. C., Potvin, P., Sarrasin, J. B., Vanhoolandt, C., Corfdir, A., Japashov, N., Mansurova, A., Tsai, C., Wu, C., Elmas, R., et al. (2025) · Trends in Neuroscience and Education · doi:10.1016/j.tine.2025.100264 · Cited by 7
Hyperbolic Deep Learning for Foundation Models: A Survey
He, N., Madhu, H., Bui, N., Yang, M., & Ying, R. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736564 · Cited by 28
ProAPO: Progressively Automatic Prompt Optimization for Visual Classification
Qu, X., Gou, G., Zhuang, J., Yu, J., Song, K., Wang, Q., Li, Y., & Xiong, G. (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/cvpr52734.2025.02341 · Cited by 30
“However, due to the hallucination in LLMs [25, 56], generated descriptions are suboptimal due to inaccurate, e.g. , “ feet ” for the food Peking Duck, or lack discrimination for fine-grained recognition, e.g. , the same descriptions “ hooked bill ” and “ webbed feet ” appear in Laysan Albatross and…”
Aldana-Martín, J. F., Durillo, J. J., Roldán‐García, M. D. M., & Nebro, A. J. (2025) · Engineering Optimization · doi:10.1080/0305215x.2025.2544215 · Cited by 4
Behind the Magic, MERLIM: Multi-Modal Evaluation Benchmark for Large Image-Language Models
Villa, A., Alcázar, J. L., Soto, Á., & Ghanem, B. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00054 · Cited by 30
“The presence of an LLM introduces additional challenges, among them the inherited tendency to Hallucinate [22, 56], resulting in the emergence of language outputs that can not be grounded to the visual input.”
LLM-Augmented Contrastive Learning for Misinformation Detection in Social Networks
Shen, H., Li, X., Wang, X., Dai, Y., Wang, T., & Bai, G. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3599080 · Cited by 7
“However, directly applying LLMs is prone to generating hallucinations [19], [20], producing plausible content but factually incorrect.”
Stack Overflow is not dead yet: Crowd answers still matter
Helić, D., & Santos, T. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.112988 · Cited by 14
“…their limited domain knowledge (recently increasingly addressed by techniques such as Retrival Augmented Generation [89]), frequent hallucinations [90], or their scaling limitations [15], still remain limiting factors in their adoption for various tasks including problem solving tasks in…”
LENS: Layers of Evaluation of Hallucination in GenAI Systems
Gu, C., Zhang, W., Huang, Z., Kou, J., Liu, Z., Zhao, C., Liu, C., Zhang, L., Lin, W., Wang, Z., et al. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189150 · Cited by 36
Towards neuroadaptive chatbots: a feasibility study
Gherman, D. E., & Zander, T. O. (2025) · Frontiers in Neuroergonomics · doi:10.3389/fnrgo.2025.1589734 · Cited by 5
“Moreover, gaining a nuanced understanding of what an annotator considers to be factually correct or incorrect, could improve the RLHF scaling by providing more human feedback data, thereby reducing the chance for hallucination in future deployed models (Huang et al., 2024).”
KnowSTU: Diagnosing Students’ Problem Behaviors Using Fine-Tuned LLM and RAG
Chen, P., Fan, Z., & Lu, Y. (2025) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2025.3625146 · Cited by 6
“Trained on massive corpora of textual data, LLMs learn statistical patterns and linguistic structures, allowing them to capture complex semantic nuances and contextual meanings [6].”
InfluentialLLM-AGR: Large Language Model Augmented Graph Representation Learning for Recommendation
Zha, X., Dong, Y., Jiang, H., Xu, Z., & Wang, C. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114791 · Cited by 16
Reimagining cancer treatments in the era of generative AI
Derbal, Y. (2025) · DIGITAL HEALTH · doi:10.1177/20552076251394631 · Cited by 4
“The inevitable LLM hallucinations 102 must also be mitigated to facilitate the adoption of GenAI-assisted clinical decision-support systems in real-world clinical setting.”
Persuasive Conversational Agents for Environmental Sustainability: A Survey
Giudici, M., Crovari, P., & Garzotto, F. (2025) · ACM Computing Surveys · doi:10.1145/3774751 · Cited by 7
Dennstädt, F., Lerch, L., Schmerder, M., Čihorić, N., Cereghetti, G. M., Gaio, R., Bonél, H., Filchenko, I., Hastings, J., Dammann, F., et al. (2025) · JAMIA Open · doi:10.1093/jamiaopen/ooaf128 · Cited by 7
“16 Potentially, the LLM occasionally fabricates information, providing results such as “BI-RADS ¼ 2” (the statistically most common classification and therefore probably also most frequent in the training data of the LLM) even when no supporting evidence exists in the text.”
Named entity recognition based on anchor span for manufacturing knowledge extraction
Li, Y., Sun, Q. Q., Zhou, C., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112693 · Cited by 4
Using LLMs to enhance code quality: A systematic literature review
Alomari, N., Redah, M., Ashraf, A., & Alshayeb, M. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107960 · Cited by 12
Li, X., Li, G., Zhao, Y., Liang, Y., Dong, Y., & Zhang, J. (2025) · Clinical Interventions in Aging · doi:10.2147/cia.s551572 · Cited by 6
“18,25,26 29 Recent investigations in musculoskeletal disorders have highlighted the potential of large language models to enhance orthopedic patient communication and clinical decision-making.”
Shekouhi, R., Holohan, M. M., Mirzalieva, O., Byrd, B., Guidry, M. F., Palines, P. A., & Chim, H. (2025) · Journal of Plastic Reconstructive & Aesthetic Surgery · doi:10.1016/j.bjps.2025.11.031 · Cited by 4
ChEdu: A Guided AI Teaching Assistant for Chemistry Education and Exam Support
Wang, X., Zhang, L., Mao, Y., McGillivray, D. J., & Wang, Z. (2025) · Journal of Chemical Education · doi:10.1021/acs.jchemed.5c00036 · Cited by 8
AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models
Cao, Z., Yang, Y., Li, X., & Zhao, H. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3635038 · Cited by 32
“Huang et al. [23] redefine the taxonomy of hallucination by introducing factuality hallucination and faithfulness hallucination, taking alignment with user directives and factual knowledge into account.”
Arous, I., Chehbouni, K., Cheng, Z., & Dossou, B. F. P. (2025) · Springer eBooks · doi:10.1007/978-981-97-8440-0_85-1 · Cited by 6
Survey of uncertainty estimation in LLMs - Sources, methods, applications, and challenges
He, J., Yu, L., Li, C., Yang, R., Chen, F., Li, K., Zhang, M., Lei, S., Zhang, X., Beigi, M., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.104057 · Cited by 26
Self-citationStorySage: Conversational Autobiography Writing Powered by a Multi-Agent Framework
Talaei, S., Li, M., Grover, K., Hippler, J. K., Yang, D., & Saberi, A. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747681 · Cited by 15
Leveraging Approximate Caching for Faster Retrieval-Augmented Generation
Bergman, S. A., Kermarrec, A.-M., Petrescu, D., Pires, R. P., Randl, M., de Vos, M., & Zhang, J. (2025) · International Middleware Conference · doi:10.1145/3721462.3770776 · Cited by 10
ICR: A framework for resolving knowledge conflicts in retrieval-augmented generation
Xiong, Y., Chen, Y., & Zhang, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132139 · Cited by 9
AI‐Enhanced Semantic Feature Norms for 786 Concepts
Suresh, S., Mukherjee, K., Giallanza, T., Yu, X., Patil, M., Cohen, J. D., & Rogers, T. T. (2025) · Topics in Cognitive Science · doi:10.1111/tops.70037 · Cited by 7
“However, challenges remain regarding the factual accuracy and reliability of these models due to issues such as hallucination(Huang et al., 2024).”
Dai, S., Wu, Q., Zhang, H., Wang, Y., & Wang, S. (2025) · Environmental Science & Technology · doi:10.1021/acs.est.5c10297 · Cited by 6
Shah, S. T. U., Hussein, M., Barcomb, A., & Moshirpour, M. (2026) · Automated Software Engineering · doi:10.1007/s10515-025-00587-5 · Cited by 6
Ding, L., Ding, N., & Shi, P. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-026-01027-w · Cited by 4
“…clues due to a lack of contextual support, which negatively affects subsequent retrieval and reasoning processes, potentially leading to hallucinations or incorrect reasoning (Huang et al., 2025 ), especially in cases where temporal information is missing or inconsistent (Shang et al., 2021).”
Orlando, G. M., Gatta, V. L., Russo, D., & Moscato, V. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104636 · Cited by 5
PALM: Synergizing Program Analysis and LLMs to Enhance Rust Unit Test Coverage
Chu, B., Feng, Y., Liu, K., Shi, H., Nan, Z., Guo, Z., & Xu, B. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00223 · Cited by 11
“While this can sometimes be affected by conflicting constraints or model hallucinations [76], potentially explaining why improvements in coverage are not always substantial on every project.”
6G AI Security: From Fundamentals to Offensive and Defensive Landscape in 6G
Braeken, A., Deac, D., Nguyen, T. T., Gür, G., Pham, Q., Yapa, C., Naranjo, P. G. V., Mora, H. C., Moremada, C., & Liyanage, M. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3659793 · Cited by 10
“Despite advanced capabilities to integrate with the 6G stack, LLM misuse and hallucinations [114] may cause serious issues related to their practical implementation.”
An Information–Theoretic Model of Abduction for Detecting Hallucinations in Explanations
Galitsky, B. A., & Rybalov, A. (2026) · Entropy · doi:10.3390/e28020173 · Cited by 7
Matharaarachchi, A., Moraliyage, H., Mills, N., Gamage, G., Silva, D. P. D., & Manic, M. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115469 · Cited by 10
Development and Evaluation of a Retrieval-Augmented Generation System for Radiology Guidelines
Komenda, A., Makowski, M., Can, E., Prucker, P., Busch, F., Wachter, A., Weller, D., Kim, S. H., Ziegelmayer, S., Bressem, K. K., et al. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01835-6 · Cited by 6
A large language model-empowered agent for reliable and robust structural analysis
Liu, J., Geng, Z., Cao, R., Cheng, L., Bocchini, P., & Cheng, M. (2026) · Structure and Infrastructure Engineering · doi:10.1080/15732479.2026.2630123 · Cited by 33
Can an AI agent lead human teams?
Simpson, J., Patil, G., Stening, H., Kamruddin, A. B., Somerville, D., Seage, S., Nalepka, P., Dras, M., Hosking, S. G., Kallen, R. W., et al. (2026) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2026.100278 · Cited by 5
Walczak, J., Tomalak, P., & Laskowski, A. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.112834 · Cited by 12
Xu, M., Li, X., Lan, T., Zeng, X., Wang, T., Sheng, S., Deng, X., Sun, J., Fiebrink, R. A., Bryan–Kinns, N., et al. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2025.2604649 · Cited by 6
Brundage, D. (2026) · Frontiers in Veterinary Science · doi:10.3389/fvets.2026.1761038 · Cited by 6
“This failure is particularly concerning given the well-documented propensity of Large Language Models (LLMs) to “hallucinate” or confabulate medical information (33–38).”
Hallucination-Aware Generative Pretrained Transformer for Cooperative Aerial Mobility Control
Ahn, H. S., Oh, S., Kim, G. S., et al. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432325 · Cited by 4
“Despite these advances, LLM-based planners may still produce hallucinated or unsafe actions due to insufficient environmental grounding [6].”
Montag, C., King, D. L., Becker, B., & Billieux, J. (2026) · Computers in Human Behavior · doi:10.1016/j.chb.2026.109006 · Cited by 7
Navigating the Risks: A Survey of Security and Privacy Threats in LLM-Based Agents
Gan, Y., Yang, Y., W, Z., He, P., Zeng, R., Wang, Y., Li, Q., Zhou, C., Li, S., Wang, T., et al. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3807666 · Cited by 119
Large language model agent for user-friendly chemical process simulations
Liang, J., Groll, N., & Sin, G. (2026) · Digital Chemical Engineering · doi:10.1016/j.dche.2026.100312 · Cited by 13
“Human oversight remains essential due to the inherent limitations of LLMs, including unpredictable failures such as hallucinations and reasoning errors [53, 54].”
IaC Generation with LLMs: An Error Taxonomy and A Study on Configuration Knowledge Injection
Nekrasov, R., Fossati, S., Kumara, I., Tamburri, D. A., & van den Heuvel, W. J. A. M. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3817608 · Cited by 17
On Controllability in Agentic AI: A Survey
Nguyen, M. H., Nguyen, D.-H., O’Sullivan, B., & Nguyen, H. D. (2026) · Minds and Machines · doi:10.1007/s11023-026-09783-y · Cited by 10
Fan, S., Wang, X., Zhang, B., & Sun, X. (2026) · Telematics and Informatics · doi:10.1016/j.tele.2026.102434 · Cited by 5
Envisioning Recommendations on an LLM-Based Agent Platform
Zhang, J., Bao, K., Wang, W., Zhang, Y., Shi, W., Xu, W., Feng, F., & Chua, T. (2025) · Communications of the ACM · doi:10.1145/3699952 · Cited by 42
“LLMs may generate hallucinations, inconsistent with factual knowledge or user inputs, 15 that can negatively affect the user experience, particularly in contexts where reliability is paramount.”
Plenary: Enhancing Engineering Education: Integrating Generative AI Tools
Mangarelli, E. (2025) · IEEE World Engineering Education Conference (EDUNINE) · doi:10.1109/edunine62377.2025.10980840 · Cited by 4
“However, these models are susceptible to inaccuracies or fabricated references commonly known as “hallucina-tions”, raising significant concerns over the reliability of LLMs in real world information retrieval [6].”
A Holistic Review of Fuzzing for Vulnerability Assessment in Industrial Network Protocols
Reda, A. M., Moustafa, N., & Lakshika, E. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3569291 · Cited by 10
“Additionally, LLMs are susceptible to hallucinations [152], occasionally producing responses that are inaccurate or misleading.”
Hao, J., Chen, L., & Meng, L. (2025) · Drones · doi:10.3390/drones9050361 · Cited by 10
Nguyen, Q.-T., Nguyen, H., Hieu, T. Q., Truong, T., Pham, V.-T., Le, L., & Williams-King, D. (2025) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3715669.3726785 · Cited by 5
“This indicates a tendency for zero-shot models to classify all samples as dyslexic, which may be caused by hallucination issues of zero-prompting in LLMs [Huang et al. 2025].”
AI-empowered health coaching for university students: A mixed-method process evaluation
Bojić, I., Ong, Q. C., Ito, S., Liu, J., Lawate, A., Palaiyan, M., Nair, E., Lwin, M. O., Theng, Y. L., Chia, M., et al. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110271 · Cited by 6
How Large Language Models Transform Urban Planning and Shape Tomorrow’s Cities?
Agrawal, K., & Göktaş, P. (2025) · The Springer series in applied machine learning · doi:10.1007/978-3-031-86039-3_8 · Cited by 9
Jonnala, S., Thomas, N. M., & Mishra, S. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1611024 · Cited by 8
“Technical risks include adversarial prompts, in which malicious inputs manipulate model behavior (Wang et al., 2023), and hallucinations, in which models generate plausible but factually incorrect outputs (Huang et al., 2025).”
A conceptual framework for human–AI collaborative genome annotation
Li, X., Whan, A., McNeil, M., Starns, D., Irons, J. L., Andrew, S. C., & Suchecki, R. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf377 · Cited by 8
“Hallucination remains a significant concern, in which models generate plausible-sounding but factually unsupported content [87].”
Zhang, Z., Gupta, P., Song, J., Zolnoori, M., & Topaz, M. (2025) · Journal of Nursing Scholarship · doi:10.1111/jnu.70039 · Cited by 5
Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards
Erak, O., Alabbasi, N., Alhussein, O., Lotfi, I., Hussein, A., Muhaidat, S., & Debbah, M. A. (2024) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshp64532.2024.11100917 · Cited by 18
“RAG also grounds the model’s response in the relevant retrieved context, reducing (yet not entirely eliminating) the risk of hallucination [6].”
Linardon, J., Thomas, J. J., Crow, S. J., Ghaderi, A., Hilbert, A., Klump, K. L., Wade, T. D., Walsh, B. T., & Weissman, R. S. (2025) · International Journal of Eating Disorders · doi:10.1002/eat.24543 · Cited by 9
Ajmal, R. H., Sarwar, M. U., Hanif, M. K., & Khan, M. I. (2025) · IEEE Access · doi:10.1109/access.2025.3613851 · Cited by 5
“Though the model’s capability has significantly increased, a persistent challenge remains in its behavior to hallucinate, i.e., produce content that appears credible but is factually inaccurate [10].”
Wang, N. X., Parpia, N. V., Parikh, A. D., & Katsaggelos, A. K. (2025) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr67560.2025.00068 · Cited by 5
Detecting AI adoption at scale: a web mining and LLM methodology
Pastor-Merino, A., Martínez-Barbero, X., & Domènech, J. (2025) · Scientometrics · doi:10.1007/s11192-025-05468-y · Cited by 11
A Conditional Companion: Lived Experiences of People with Mental Health Disorders Using LLMs
Purohit, A. K., & Heuer, H. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791763 · Cited by 11
Mitigative Strategies for Recovering From Large Language Model Trust Violations
Martell, M. J., Baweja, J. A., & Dreslin, B. D. (2024) · Journal of Cognitive Engineering and Decision Making · doi:10.1177/15553434241303577 · Cited by 13
“LLMs may also fail by hallu-cinating, or generating content that is either fac-tually inaccurate or misleading (Huang et al., 2024; Xu et al., 2024).”
A Smart Recommender System for Stroke Risk Assessment with an Integrated Strokebot
Argymbay, M., Khan, S., Ahmad, N., Salih, M., & Mamatjan, Y. (2024) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-024-00922-3 · Cited by 6
Incentive Distributed Knowledge Graph Market for Generative Artificial Intelligence in IoT
Hao, G., Pan, Q., & Wu, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3522191 · Cited by 6
“To address the above challenges, researchers have found that knowledge graph (KG) can enhance GAI training, reasoning, and interpretability, thereby improving GAI’s knowledge learning and generation capabilities [7], [8], [9].”
Problematic Tokens: Tokenizer Bias in Large Language Models
Yang, J., Wang, Z., Lin, Y., & Zhao, Z. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825615 · Cited by 16
“The English text was translated by human beings for reference. dataset result in critical hallucinations [1], [2].”
Li, B., Liu, T., Ma, J., Dai, J., & Liao, P. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111074 · Cited by 5
Self-citationRoll, D. S., Kurt, Z., Li, Y., & Woo, W. L. (2025) · Sensors · doi:10.3390/s25113352 · Cited by 8
“This is thought to arise from a model’s tendency to produce outputs based on learned patterns without grounding in factual data, which can lead to myriad problems with its application or validity, especially in high-risk scenarios such as healthcare diagnosis assistance [16].”
Chen, W., Liu, C., Huang, W., Lyu, J., Yang, M., Du, Y., Du, L., & Yang, J. (2025) · International Symposium of Electronics Design Automation (ISEDA) · doi:10.1109/iseda65950.2025.11100397 · Cited by 5
“Additionally, inherent limitations like hallucination phenomena necessitate rigorous verification and iterative refinement of LLMs’ outputs to ensure reliability [15].”
Large language modeling of hallucinatory problem mitigation based on the wheel of emotions
Wang, Z., Wang, J., Zhou, L., & You, F. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107996 · Cited by 7
ZiGong 1.0: A Large Language Model for Financial Credit
Lei, Y., Wang, Z., Liu, C., & Wang, T. (2025) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew67478.2025.00038 · Cited by 10
“Moreover, Large Language Models (LLMs) in the financial credit domain still suffer from issues such as hallucinations (Huang et al., 2024) and knowledge forgetting (Luo et al., 2023).”
Hrčková, A., Móro, R., Srba, I., Šimko, J., & Bieliková, M. (2025) · ACM Journal on Responsible Computing · doi:10.1145/3764592 · Cited by 19
Madrid-García, A., Benavent, D., Plasencia-Rodríguez, C., Rosales, Z., Barbancho, B. M., & Freites, D. (2025) · medRxiv · doi:10.1101/2025.04.10.25325588 · Cited by 5
“This approach offers several advantages: it allows the integration of proprietary and private data without additional training, produces more grounded responses mitigating medical hallucinations [9,19], and enables the use of up-to-date information beyond the model’s training cutoff.”
A Narrative Review of Artificial Intelligence in Medical Diagnostics
Hirosawa, T., & Shimizu, T. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.063803 · Cited by 11
Bio-Eng-LLM AI Assist: A modular chatbot platform for interdisciplinary research and education
Forootani, A., Aliabadi, D. E., & Thrän, D. (2025) · SoftwareX · doi:10.1016/j.softx.2025.102260 · Cited by 10
A Review of LLM Agent Applications in Finance and BankingPreprint
Batra, D., Hamill, C. B., Hartley, J., Okhrati, R., Seddon, D., Miller, H., Khraishi, R., & Cowan, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5381584 · Cited by 15
Wahl, B., Nassiri-Ansari, T., Redpath, D. D., Allotey, P., & Schwalbe, N. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001302 · Cited by 4
“They note that LLMs can sometimes produce misleading summaries or “halluci-nated” references if not tethered to verified datasets [32].”
AI4Research: a survey of artificial intelligence for scientific research
Chen, Q., Yang, M., Qin, L., Liu, J., Yan, Z., Guan, J., Peng, D., Ji, Y., Li, H., Hu, M., et al. (2026) · Science China Information Sciences · doi:10.1007/s11432-025-5000-y · Cited by 4
Self-citationExternal Data Extraction Attacks Against Retrieval-Augmented Large Language Models
He, Y., Chen, Y., Li, Y., Shao, S., Qi, L., Li, B., Tao, D., & Qin, Z. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3705326 · Cited by 4
“A primary reason for these shortcomings is often the absence of relevant information within the model’s training data [4].”
FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
Sui, Y., He, Y., Liu, N., He, X., Wang, K., & Hooi, B. (2024) · arXiv · doi:10.48550/arxiv.2405.13873 · Cited by 4
Alnaimat, F., AlSamhori, A. R. F., El Sharu, H., Othman, L., Oralbek, A., & Zimba, O. (2025) · Journal of Korean Medical Science · doi:10.3346/jkms.2025.40.e342 · Cited by 4
“40 Therefore, this review’s synthesis suggests that no single AI tool is a complete solution for statistical review.”
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.