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 1,001–1,100 of 2,245
Suzgen, E. E., Şahin, M. E., Bakir, M., Arisoy, Ç., Ulutaş, E. G., Günay, R. B., Yildiz, G., & Ulutaş, H. (2026) · 2026 2nd International Symposium on AI-Driven Engineering Systems (ISADES) · doi:10.1109/isades69945.2026.11608117
Structured Schemas for Provenance‐Rich, LLM ‐Assisted QSP Model Calibration
Eliason, J., & Popel, A. S. (2026) · CPT: Pharmacometrics & Systems Pharmacology · doi:10.1002/psp4.70306
Nguyen, T. T., & Nguyen Huynh Hoai, P. (2026) · Proceedings of the 14th International Conference on Advances in Information Technology · doi:10.1145/3816713.3820249
Niimi, J. (2025) · arXiv · doi:10.48550/arxiv.2510.25378 · Cited by 7
“Hallucination in LLMs has been examined from diverse perspectives [2, 4, 13, 14, 15].”
Explainability in AI: Comparing Human-Like and System-Like Trust Repair Strategies
Konopka, B., & Wiesche, M. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10751-1 · Cited by 1
Ansari, S. (2026) · arXiv · doi:10.48550/arxiv.2602.05930 · Cited by 28
“LLMs are known to hallucinate 2 , 3 , generating fluent, confident-sounding text that is factually incorrect [5, 6].”
Küçükuncular, A. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02318-5 · Cited by 1
“Recent taxonomic work distinguishes at least seven cases [15, 18].”
InfluentialDeceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Caruzzo, C., Yoo, D., & Kim, T. S. (2026) · arXiv · doi:10.48550/arxiv.2607.09349
“Existing frameworks verify that LLM outputs are consistent with source documents or factual knowledge [Maynez et al., 2020, Ji et al., 2023, Huang et al., 2025] and that RAG responses accurately reflect retrieved content with genuine citations [Gao et al., 2023, Asai et al., 2024, Es et al., 2024,…”
Tsui, K. (2025) · arXiv · doi:10.48550/arxiv.2507.02778 · Cited by 29
“However, despite their impressive capabilities, LLMs are known to exhibit unpredictable failures and generate inaccurate information (Maynez et al., 2020; Huang et al., 2025; Bang et al., 2023; Shi et al., 2023), or explore an unproductive reasoning path and commit to it.”
Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences
Russinovich, M., Kumar, R. S. S., & Salem, A. (2026) · arXiv · doi:10.48550/arxiv.2607.00738 · Cited by 4
“More broadly, hallucination has been surveyed extensively [1], [2], [3] and quantified by benchmarks such as TruthfulQA [20], HaluEval [21], and FActScore [22], building on faithfulness studies in summarization [23], [24].”
Threats or Opportunities? Enhancing Firm Performance in the Era of Generative AIPreprint
Lee, S. J., Lehmann, J., Chae, H., Shin, D.-H., Auh, S., & Han, S. P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4771103
Benchmarking Biomedical Relation Knowledge in Large Language Models
Zhang, F., Yang, K., Zhao, C., Li, H., Xin, D., Tian, H., & Zhou, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5131-0_41
A New Approach to Managing Smart Environment Infrastructure Settings
Dik, G., Богданов, А. В., Shchegoleva, N., Dik, A., & Kiyamov, J. U. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-65308-7_28
Xie, X. C., Chen, R., Peng, T., Lin, D. X., & Cui, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7244-5_8 · Cited by 1
Nominal Compound Chain Extraction Enhanced by Chain-of-Thought Information
Li, C., Zhang, L., Guo, H., & Zheng, Q. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9443-0_28
Large Language Model for Querying Databases in Portuguese
Figueiredo, L., Pinheiro, P., Cavique, L., & Marques, N. C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73503-5_1
Legal Judgment Prediction Through Argument Analysis
Azmi, Mistica, M., Levy, I., & Hovy, E. H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0348-0_4
Evaluating Large Language Models for Healthcare: Insights from MCQ Evaluation
Lin, S., Osop, H., Zhang, M., & Huang, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0865-2_22
Similarity based task timely termination method for image based intelligent agents
Jie, S., Huang, X., Jing, C., Jiang, X., & Dong, L. (2024) · Scientific Reports · doi:10.1038/s41598-024-83463-8
Understanding the Roles of Visual Modality in Multimodal Dialogue: An Empirical Study
Cao, Q., Song, R., & Chen, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-2071-5_20
Krestel, R. (2025) · Information - Wissenschaft & Praxis · doi:10.1515/iwp-2024-2049
A Framework for Vietnamese Question-Answering in Law Domain
Le, T. V. Q., Vu, D.-H., Pham, V.-H., Le, A.-C., & Nguyen, N. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00108 · Cited by 1
“One of the main issues with LLMs is that they sometimes "hallucinate" [6].”
Multi-MELO: Unified multimodal model editing with dynamic LoRA
Chen, Q., Yin, J., Yu, L., Zhou, J., & He, L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126766 · Cited by 3
Self-citationAddressing LLM Challenges: A Hybrid Framework for Duplicate Question Detection
Hsu, H.-H., & Huang, N.-F. (2024) · International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC) · doi:10.1109/icairc64177.2024.10900148
“However, employing LLMs in specialized fields presents significant challenges, with one of the most critical issues being hallucinations and inaccurate responses [7][8].”
Pan, Z., Peng, Y., Jian, Z., Chen, Y., Qiu, W., Ma, H., Yao, J., Wang, M., & Wu, Q. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890213
“Moreover, when the data format or the user’s expression changes, LLMs are prone to hallucinations, making it difficult to adapt to real-world applications [9]–[11].”
Impact of Temporal Precision on Speech Synthesis Accuracy From Electrocorticographic Brain Signals
Rabbani, Q., Fifer, M. S., Crone, N. E., & Moro-Velázquez, L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888813 · Cited by 2
“This aligns with the known tendency of RNNs to produce data-independent artifacts, often referred to in the deep learning literature as network hallucinations [25], [26], [27].”
Text2RLab: No-Code Methodology for Robotic Programming and Interaction in Laboratory Tasks
Yordanova, K., Stoev, T., Rebl, H., Hahn, O., & Peters, K. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716350
Verma, T., Panda, P., Sharma, P., Sharma, Y. D., & Sharma, S. (2024) · International Conference on Electrical and Computer Engineering Researches (ICECER) · doi:10.1109/icecer62944.2024.10920351
“A plausible inference can be made that on increasing input context the LLM models tend to hallucinate[13] resulting in erroneous behaviour.”
MVP-MCTS: Language Modelling a Flexible Multi-Agent Planning Framework
Li, Z., & Ji, J. (2024) · International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM) · doi:10.1109/aiim64537.2024.10934217 · Cited by 2
“Our prompts are designed in a simple and clean manner so as to mitigate the problem of hallucination [3] on part of the language model.”
TLDR: Text Based Last-Layer Retraining for Debiasing Image Classifiers
Park, J., Jeong, S., & Moon, T. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00252 · Cited by 1
“Despite the impressive generation capability of LLMs, it is well-known that they can exhibit hallucinations and provide inaccurate information [10, 35].”
Az AI-eszközök hatása a programozók munkájára és munkaerőpiaci kilátásaira
Szabados, L. (2025) · Vezetéstudomány / Budapest Management Review · doi:10.14267/veztud.2025.04.04 · Cited by 2
Research on Automatic Question Generation Methods for Niche Subjects Based on Large Language Models
Guo, M., Sun, B., He, J. Y. D., & Zhang, F. (2025) · International Conference on Educational and Information Technology · doi:10.1109/iceit64364.2025.10976111 · Cited by 1
“Furthermore, the content generated by LLMs often relies heavily on pre-trained data, which can result in the generation of inaccurate or hallucinatory information in the absence of sufficient domain-specific knowledge[9].”
Chen, Y., Hu, G., Xia, C., Yu, L., Popescu, M., & Xu, D. H. (2025) · International Journal of Artificial Intelligence and Robotics Research · doi:10.1142/s2972335325300019 · Cited by 2
Yepez, J., Tavares, B., Peres, F. D. C. L., & Becker, K. E. (2024) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat62293.2024.00026
“In addition to prompt design, challenges for the use of LLM include hallucinations (i.e., the model returns non-sense or irrelevant answers) [19], or dealing with the non-deterministic nature of LLMs (i.e., the same prompt can generate different answers).”
ArcTEX—a novel clinical data enrichment pipeline to support real-world evidence oncology studies
Tait, K., Cronin, J., Wiper, O., Wallis, J., Davies, J., & Dürichen, R. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1561358 · Cited by 1
“Because GMs are developed to provide plausible responses to prompts, it can be dif fi cult to determine whether the generated response is factual or a hallucination (41).”
Research on Technical Route of AI Large Models for Electric Power Knowledge Services
Peng, S., Xiao, J., Zhang, W., Zuo, Y., Liu, S., Long, Y., Huang, Z., & Wu, S. (2024) · IEEE Conference on Energy Internet and Energy System Integration (EI2) · doi:10.1109/ei264398.2024.10990616
“3)The implementation of universal large models in the power industry requires addressing the problem of ‘ large model illusion ’ , where large models are prone to generating inaccurate information and providing answers that violate user input, contradict context, or conflict with facts[4].”
Architectures of Error: A Philosophical Inquiry into AI and Human Code GenerationPreprint
Sartori, C. C. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5265751
Agentware in Software Engineering: A Taxonomy for Leveraging Llms-Based Multi-Agent SystemsPreprint
Sipio, C. D., Oliveira, M. C. S. D., Ruscio, D. D., Nguyen, P. T., & Rubei, R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5273078 · Cited by 2
Innovating IT Ethics Education: The Role of AI in Course Development
Lorenz, B., & Kikkas, K. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93564-0_20
Varer, B., & Мокін, В. Б. (2025) · Information Technology and Computer Engineering · doi:10.63341/vitce/1.2025.69
“The presence of “hallucinations” in LLMs is a known issue, as the models can generate false or incorrect information, which may nonetheless appear plausible, making it difficult to detect and verify (Huang et al ., 2025).”
Identifying and overcoming challenges in generative AI: a user innovation perspective
Garg, J., Singh, A. K., Verma, S., & Chauhan, R. (2025) · International Journal of Innovation Science · doi:10.1108/ijis-10-2024-0296 · Cited by 1
Introduction to the special issue
Holste, A., & Agnetta, M. (2025) · Lebende Sprachen · doi:10.1515/les-2025-0011
Generative AI Interface Design Considerations for Private Equity
Anderson, S., & Zhao, Y. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94168-9_1
Goethals, S., Sedoc, J., & Provost, F. J. (2025) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3708319.3733656 · Cited by 4
Augmenting the Generality and Performance of Large Language Models for Software Engineering
Peña, F. C. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse-companion66252.2025.00059 · Cited by 1
Opinion: The need for higher education in lighting: Human insight in a digital age
Mander, S. (2025) · Lighting Research & Technology · doi:10.1177/14771535251349693
Zhang, H., & Shafiq, M. O. (2025) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc64641.2025.00032 · Cited by 2
“However, LLMs can hallucinate [2] and generate incorrect answers, which is a critical issue in some fields, such as medicine.”
Sekwenz, M.-T., Gsenger, R., Stocker, V., Görnemann, E., Talypova, D., Parkin, S. E., Greminger, L., & Smaragdakis, G. (2025) · Annual Symposium on Human-Computer Interaction for Work (CHIWORK) · doi:10.1145/3707640.3731929 · Cited by 2
Learned Lessons—Recommendations
Eidel, B., Narkhede, R., & Neelakandan, A. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-85470-5_11
MSKE-LLM: Multi-Stage Knowledge Enhancement Policy Question-Answering Large Language Model
Wang, G., Qiao, Z., Guo, Q., Liang, S., Lin, H., & Yang, C. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033430
“The hallucinatory issues of LLMs [2] can result in irrelevant or erroneous policy recommendations, potentially offering users misguided guidance and leading to severe consequences.”
Guan, W., Liu, H., Li, X., Zhou, J. J., & Yan, Y. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033484 · Cited by 1
“The problem mentioned above, known as the hallucination of LLMs [5], significantly impedes their application in many real-life scenarios.”
Streamrag: a Lock-Aware and Traffic-Aware Query Coordinator in Stream-Based Rag Systems
Jeong, Y., Park, K., & Park, S. (2025) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid64434.2025.00065 · Cited by 1
I Hear You: On Human Knowledge and Vocal Intelligence
Holenstein, M. A. (2025) · Revista Lusófona de Estudos Culturais · doi:10.21814/rlec.6316
Zhou, H., Zhu, Z., Hong, S.-S., & Oh, K. M. (2025) · doi:10.2196/preprints.79975
Cheng, S.-C., & Yang, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98197-5_37
Hallucination Detection in LLMs via Beam Search Sampling and Semantic Consistency Analysis
Bouchekir, R., Faghih, F., & Beyene, T. A. (2025) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w65791.2025.00076 · Cited by 3
“This phenomenon, referred to as factual hallucinations, occurs when generated content strays from verifiable real-world facts [9].”
Retrieval-Augmented Generation for Smart Classroom Applications
Zhengyuan, F., Yan-li, L., & Zhang, H. (2025) · International Conference on Computing, Networks and Internet of Things (CNIOT) · doi:10.1109/cniot65435.2025.11070736
Bu, K., Wang, Z., Zhu, P., Isaev, P., Chen, W., Xu, T., & Liu, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9946-9_10
Paturu, M. K., Parameswaran, G., Naga Tanmay, P., & Ashok Kumar, T. (2025) · International Conference on Inventive Computing and Informatics (ICICI) · doi:10.1109/icici65870.2025.11069889 · Cited by 2
“This would increase the model reliability and ensure that extracted data is both accurate and contextually relevant [31], [32].”
Chen, D., Hu, D., & Li, L. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9994-0_33
Zhao, C., Zeng, B., Chen, K., & Lin, X. A. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9994-0_39
Evaluating Human-Large Language Model Alignment in Authorship Attribution
He, Y., & Du, H. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9994-0_28
Task-Classifying Retrieval Augmented Generation
Ju, J., Zang, P., Zhong, H., & Wang, L. (2025) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd64986.2025.11082008 · Cited by 1
“This is particularly prominent in scenarios that require handling the latest information or domain - specific knowledge [5][6][7].”
Transforming Digital Access in Parliament: Topic Modeling Meets Retrieval Augmented Generation
Matoshi, V., Singh, S. S., Kucera, J., Meyer, P., & Gygli, M. (2025) · International Conference on eDemocracy & eGovernment · doi:10.1109/icedeg65568.2025.11081627
“However, a well-documented issue with LLMs is their tendency to hallucinate [7].”
Evaluating the Accuracy of AI Content DetectorsPreprint
YILDIZ, F. E., Karaarslan, E., & Aydın, Ö. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5364392
AutoBackend: Agent-Driven Framework for Intelligent Backend Development
Lin, R., Hu, B., & Zhang, Z. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9986-5_35
WildVideo: Benchmarking LMMs for Understanding Video-Language Interaction
Yang, S., Yu, W., Yang, W., Liu, X., Tan, H., Lan, L., & Xiao, N. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3592831 · Cited by 8
“In the NLP community, hallucinations are typically categorized into two types [37]: 1) factual hallucinations, which emphasize the inconsistency between the generated content and verifiable real-world facts, usually manifesting as factual inaccuracies or fabrications; and 2) faithful hallucinations,…”
Self-citationXu, J., Chen, Z., Jiang, Z., Zhao, D., & Li, L. (2025) · IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) · doi:10.1109/icps65515.2025.11087829 · Cited by 2
“While this research has yielded some results, it has also exposed several challenges, particularly in the lack of domain-specific knowledge and the hallucination phenomenon [6].”
The Ordinary MKeaning Bot: Simulating Human Surveys with LLMsPreprint
Kruse, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5378203
Research on Normative Chalkboard Writing Question Answering Based on Large Language Models
Gao, F., & Li, C. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-0011-6_44
Multi-round Q&A Hallucination Analysis of LLMs in Geographical Education
Chen, H., Kong, D., Li, X., & Wang, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9891-2_2
Towards Step-Aware ITSs: Generation and Evaluation of Synthetic Step-by-Step Exercise Solutions
Russo, F., Calò, T., & Russis, L. D. (2025) · ACM Conference on Learning @ Scale (L@S) · doi:10.1145/3698205.3733940
SC-Telco RAG: Enhancing RAG through Structured Contexts in Telecommunications
Du, J., Ding, J., Li, J., Wang, X., Ye, X., & Ouyang, Y. (2024) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshp64532.2024.11100862 · Cited by 1
“Due to the above challenges, LLMs may produce hallucinations or fabricate information when answering questions, which may seriously damage the reliability and practicality of their output in critical applications [3].”
LLM Re-Ranker as a Tool for Enhancing Sequential Recommendations
Vaidyanathan, K. G., Varun, M. V., & Das, B. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-92611-2_2
Evolutionary Landscape of Artificial Intelligence in Education: Review and Prospects
Jing, X., Feng, Z., Yang, X., Wang, Z., & Li, W. H. (2025) · International Symposium on Educational Technology · doi:10.1109/iset65607.2025.00042 · Cited by 2
“LLMs currently exhibit limitations, notably a relatively high rate of hallucination, in which the model produces plausible but factually inaccurate information, and its “black box” nature that makes it difficult to determine output validity and reliability [15], [37], [38].”
Self-citationA Pilot Study of Probing Before Trusting Large Language Models in Self-Learning
Wei, Z., Lee, V. C. S., & Chan, W. K. (2025) · International Symposium on Educational Technology · doi:10.1109/iset65607.2025.00046
“Despite their impressive capabilities, LLMs are prone to AI hallucinations [10], which refers to when they generate outputs that are incorrect, misleading, or entirely fabricated, often presenting them with unwarranted confidence.”
Villardar, K. J., & Aliac, C. J. G. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-99965-9_15 · Cited by 3
Towards a RAG-Based Framework for Accounting Practices: Context-Aware Question Generation
Bahri, A., & Oueslati, W. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-04225-5_3 · Cited by 1
Feng, Z.-Y., Zhang, X., Wang, H., Hong, X., Zhan, J., & Zhou, Y.-Q. (2025) · bioRxiv · doi:10.1101/2025.08.12.669850 · Cited by 1
“On the other hand, fine-tuning the language model with all parameters [29,30] on the glycosylation dataset not only requires substantial computational resources but also may risk fundamentally altering the model's original capabilities and causing overfitting.”
Self-citationAccelerating Insight Discovery in Large Biomedical Text with Scalable Processing FrameworkPreprint
Kim, D., Hauptman, M., & Patrick, M. T. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.08.14.670384
“LLMs are known to exhibit hallucinations (Huang et al., 2025), generating confident but inaccurate responses that can compromise the reliability of downstream research or clinical applications.”
Automated Feedback Loops to Protect Text Simplification with Generative AI from Information Loss
Nandiraju, A. K. S. K., Gondy Leroy, A., Kauchak, D., & Ahmed, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00071-2_31 · Cited by 3
“In addition to this, LLMs are also prone to produce incorrect information that is factually wrong or ambiguous to evaluate based on the original source information [28].”
Qin, X., Hu, Y., Wu, W., Li, X., & Yin, Q. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9080209 · Cited by 2
Zhao, S., Zhang, G., Liu, S., Zhang, J., Bandara, H. M. N. D., Zhong, R. Y., & Wang, L. (2025) · Engineering · doi:10.1016/j.eng.2025.08.023 · Cited by 3
Macedo‐Rouet, M. (2025) · The Conversation · doi:10.64628/aak.tasjqgy3d
Language AIs in 2024: Size, guardrails and steps toward AI agents
Licato, J. (2024) · The Conversation · doi:10.64628/aai.qxp9ecw9d
Chain-of-Summary: An Efficient Multi-Clustering Framework for Hierarchical Abstraction
Yang, C., Zhu, W., Yang, Z., Liu, C., & Hong, J. (2025) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac65507.2025.00090 · Cited by 1
“However, when dealing with real-world applications requiring up-to-date and accurate information, LLMs face a critical challenge: the tendency to generate outdated or inaccurate content, commonly known as ”hallucination” [1].”
Murakami, S., Oumi, K., Hirata, K., & Ogasawara, K. (2025) · doi:10.2196/preprints.83247
Andrushevich, A., Goylo, A., Sadouski, M., & Kovalev, M. (2025) · Springer eBooks · doi:10.1007/978-3-032-01628-7_23
Reduction of supervision for biomedical knowledge discovery
Theodoropoulos, C., Coman, A. C., Henderson, J., & Moens, M. (2025) · BMC Bioinformatics · doi:10.1186/s12859-025-06187-0 · Cited by 1
An Overview of Artificial Intelligence in Neurology
Parker, T., & Brush, B. (2025) · Seminars in Neurology · doi:10.1055/a-2693-0547 · Cited by 2
Kim, S. H., Park, D. C., Lee, S. Y., Lee, S. Y., & Chong, Y. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101392 · Cited by 5
Epstein, M. D., & Seielstad, C. (2025) · International Journal of Wildland Fire · doi:10.1071/wf25051
Xu, W., Wan, H., Antonopoulos, C., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5447218
AI for ESG Governance in South Africa: A Systematic Review of Financial Intelligence ApproachesPreprint
Mathebula, M., Modupe, A., Marivate, V. N., & du Toit, E. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5443142 · Cited by 1
Kurulkar, G., Ingale, S., Shinde, A., Jangale, Y. N., & Itkar, S. A. (2025) · Cureus Journal of Computer Science. · doi:10.7759/s44389-025-05957-4
“Discussions on process-oriented summarization have been referenced by this automated quiz generator, which asserts that although LLM-based summarizers provide enhancements in fluency and contextual relevance, problems such as incoherence remain [4,5].”
Exploring the Causes of Hallucinatory Phenomena and Coping Strategies in the Big Language Model
Lu, M. (2025) · ITM Web of Conferences · doi:10.1051/itmconf/20257804018
AI-Assisted Curation: A Framework for Curatorial Materials
Li, Q., & She, J. P. M. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152075 · Cited by 1
“However, studies by Huang et al. [2] and Wang et al. [3] highlight the tendency of large language models’ (LLMs) toward ’hallucinations’ in textual and visual analysis.”
ASMem: Anchor sparse memory for multi-domain knowledge editing of large language models
Zheng, G., Wang, Z., Zhao, Y., He, T., Wang, X., Wang, H., Zhao, T., & Zong, C. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109230
Self-citationYu, G., Yan, L., Niu, J., Gao, D., & Yuan, X. (2025) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac65194.2025.11166604 · Cited by 1
Performance Analysis of General and Custom GPTs in L2 Personalized Interaction
Wu, Y., Zou, X., Su, H., & Lau, K. (2025) · doi:10.1109/icaie64856.2025.11158472
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.