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 1,501–1,600 of 2,245
Mitigating Intrinsic Hallucinations Using Orthogonal Fine-Tuning and Dirichlet Prior Calibration
Kaushal, S., Singh, C., Bijalwan, V., & Mohana, R. (2026) · World Conference on Computational Science and Technology (WcCST) · doi:10.1109/wccst67302.2026.11495718
DocMind: Conversational PDF QA with RAG
Rakshitha, B., Dharuni, R., Likhitha, M., Lakshmi, S., & Kumar, V. R. (2026) · International Electronics & Packaging Technologies Conference: Bridging Skills & Innovation for India's Industry (EPT India) · doi:10.1109/epdmc67535.2026.11496558
“Although Large Language Models (LLMs) like GPT-4 and Claude are creating conversational AI and chat interactions, they hallucinate, returning factually incorrect information with great confidence [1] [2] [3].”
Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation
Zhang, H., Hashimoto, A., & Hirasawa, T. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00298
HalluciSafe: Entailment-Driven Hallucination Suppression in LLM-Assisted Manuscripts
Abirami, A., & Ponmaniraj, S. (2026) · World Conference on Computational Science and Technology (WcCST) · doi:10.1109/wccst67302.2026.11496072
“Hallucinations in academic manuscripts can be in the form of falsified statistics, wrong methodological overviews, unbased scientific assertions, or fictitious references [2].”
Meta-Edu: An Adaptive Multi-Agent Framework for Educational Content Generation and Assessment
Sinha, S. R., Parikh, A., & Sweta, S. (2026) · IEEE International Conference on AI Engineering and Innovations (AIEI) · doi:10.1109/aiei69164.2026.11497270
“…between intrinsic hallucinations (which contradict source knowledge) and extrinsic hallucinations (which cannot be verified), and factors like a lack of sufficient or biased training data, RLHF misalignment, and greedy or uncontrolled decoding strategies contribute to such hallucinations [1].”
InfluentialGhosal, R., Middya, A. I., & Roy, S. (2026) · IEEE International Conference on AI Engineering and Innovations (AIEI) · doi:10.1109/aiei69164.2026.11496917
“Acommon challenge in LLMs is hallucination, where outputs seem acceptable but differ from ground truth [13].”
Harwardt, M., & Prause, M. (2026) · Springer eBooks · doi:10.1007/978-3-658-50907-1_1
Fact-Aware Text Generation for Low-Resource Languages: A Systematic Survey with Emphasis on Marathi
Ghorpade, M., & Patankar, S. (2026) · IEEE International Conference on AI Engineering and Innovations (AIEI) · doi:10.1109/aiei69164.2026.11497956
“The hallucinations in the LLMs are generally divided into intrinsic and extrinsic as per the available research, and systematic taxonomies are offered to describe the causes of hallucinations and their patterns of appearance [1], [7].”
Supporting Reviewing Reviews: How HCI Authors Handle Peer Reviews of Manuscripts
Yeung, C. A., Stark, J., Li, J., Chevalier, F., Park, J., Kim, Y., & Tang, A. (2025) · International Conference on Human-Engaged Computing (ICHEC) · doi:10.1145/3786995.3786998
Минимизация ошибок нейросетевых моделей в библиотечно-издательской сфере: подходы и их эффективность
Рзянкин, И. С. (2025) · Sovremennye informacionnye tehnologii i IT-obrazovanie. · doi:10.25559/sitito.021.202502.272-286
Evaluating User Preferences for Gender and Embodiment Scope in Human-Agent Interaction Systems
Yan, K., Bu, T., Ye, J., Xu, X., & Yang, L. (2025) · International Conference on Human-Engaged Computing (ICHEC) · doi:10.1145/3786995.3787057
A generative AI-Enhanced hybrid framework for reliable long-term photovoltaic power forecasting
Qi, Y., Lou, C., & Yang, J. (2026) · Energy and AI · doi:10.1016/j.egyai.2026.100760
When Machines Confabulate: Understanding and Addressing Hallucinations in Large Language Models
Raunak, M. S. (2026) · Computer · doi:10.1109/mc.2026.3673606
Xiong, J. (2026) · AI & Innovation · doi:10.1002/aiv2.70003
Maharjan, R., & Ryu, S. I. (2026) · Annual Symposium on HCI Education (EduCHI) · doi:10.1145/3803869.3803871 · Cited by 1
Shao, A., & Scheufele, D. A. (2026) · Journal of Broadcasting & Electronic Media · doi:10.1080/08838151.2026.2669539 · Cited by 2
Kim, E. J., & Lim, J. H. (2026) · Journal of the Computational Structural Engineering Institute of Korea · doi:10.7734/coseik.2026.39.2.123
Method Distinction for Hallucination Detection
Gupta, B. P., Gayratovich, E. N., & Madaminov, B. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7320-1.ch007
Pisco: An Isolation Bug Case Reduction and Deduplication Framework
Weng, S., Yang, H., Hu, Z., Zhang, R., Pan, Z., Yang, C., Zhou, X., Chen, Y., He, X., & Pan, A. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3797919.3797944
DeepInflation: An AI Agent for Research and Model Discovery of Inflation
Peng, Z.-Y., Yuan, H.-S., Lai, Q., Lan, Q.-Y., Wang, Z.-H., Jiang, J.-Q., Ye, G., Zhang, J., & Yun-song Piao, A. (2026) · Research in Astronomy and Astrophysics · doi:10.1088/1674-4527/ae6ad8 · Cited by 14
A comprehensive survey of pretrained models for autonomous driving: Methods and applications
Hu, R., Yin, Z., Nie, L., Zhou, Y., & Guo, H. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104457
Hallucination-Aware, Injection-Resistant LLMs for Scientific Text Integrity
Bhardwaj, N., Bhardwaj, A., & Garg, L. (2025) · International Conference on Sustainable Computing and Smart Systems (ICSCSS) · doi:10.1109/icscss64956.2025.11501150
“Despite improvements in architecture and training, hallucinations remain prevalent across both open-domain and specialized model variants [13].”
Gamification for Inclusive Large Language Models
Samimi-Dehkordi, L., Kolahdouz-Rahimi, S., & Fatima, S. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6063-8.ch003
Target Recommendation for Home AI Device Control Commands
Madhumitha, S. D., Jeevakumari, S. A. A., & Mandal, A. K. (2026) · International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI) · doi:10.1109/raeeucci67649.2026.11504948
“Low-confidence cases are blocked and routed to fallback, reducing hallucination-driven actuation risk [7].”
Takahashi, Y., Kadoya, N., Arai, K., TANNO, H., Tanaka, S., Katsuta, Y., Hoshino, T., Harada, H., Omata, S., Yamamoto, T., et al. (2026) · Journal of Radiation Research · doi:10.1093/jrr/rrag019
Bao, W., Wang, Y. A., Gao, R., Leng, F., Bao, Y., & Yu, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0378-9_22 · Cited by 1
“[8,32,6,24,16,18,17].”
Enhancing Outcome Based Education with Data Science: A Case Study at Parul University
Agal, S., Raulji, K. M., Parashar, P., & Shekokar, K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-22567-2_26
Leveraging AI chatbots in supporting breast and ovarian cancer patients: A scoping review
Hui, V. C. C., Tian, L., Feng, X., Yuan, X., Yorke, J., & Lee, Y. J. (2026) · Digital Health · doi:10.1177/20552076261451390 · Cited by 1
“61 In oncology settings, such errors could directly influence patient decision-making regarding treatment or genetic testing, potentially leading to delayed diagnoses or the pursuit of clinically inappropriate interventions.”
Self-citationConsensus-on-Graph: Plan-Driven Exploration and Consensus Decision-Making on Knowledge Graphs
Hu, C., Zhan, B., Yuan, L., Fan, W., & Yan, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0369-7_32
PawMed Bot: A Retrieval-Grounded AI System for Evidence-Based Veterinary Care
Saha, P., Poornashree, E., & Kavitha, G. (2026) · IEEE International Conference for Convergence in Computing Technology (I3CTCON) · doi:10.1109/i3ctcon68242.2026.11508088
“While these can sound natural and even appealing, they often lack sound medical substance and are capable of issuing faulty or dangerous advice Misreading a symptom or misinterpreting a sign may imply a delay in proper treatment or an action inappropriate for the case [4], [10].”
Generative AI in Surgical Care: Evaluating Large Language Model Performance in Patient Education
Hall, A. E., Patel, A. K., Shariati, K., Perrotta, A. T., Argame, A. A., Tseng, C. Y., Tseng, C., Hidalgo, M. A., & Lee, J. C. (2025) · Journal of Artificial Intelligence for Medical Sciences · doi:10.55578/joaims.251202.001
“…particularly significant given that LLMs gather data through large-scale web scraping, publicly available datasets, and reinforcement learning, and have been observed to generate hallucinations, a phenomenon where fabrication or misleading information appears credible but lacks factual bias [124].”
Automatic Knowledge Gap Detection and Plan Validation Using Counterfactual Justifications
Tudor, A. R., Arias, J., & Gupta, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0184-6_13
Wang, K., Wang, T., Wang, B., Li, Q., Liu, Y., Han, Q., Zhang, C. L., & Ren, Y. (2026) · Reviews in Fish Biology and Fisheries · doi:10.1007/s11160-026-10058-z · Cited by 2
“A primary concern is inaccurate output, including factual errors or more deceptive “hallucinations” (Huang et al. 2025), which appear plausible but are actually incorrect.”
Large Language Models for Binary Decompilation: Paradigms, Evaluation, and Challenges
Wang, Y., Tian, Y., Wei, H., & Wang, F. (2026) · International Conference on Computer Network Security and Software Engineering (CNSSE) · doi:10.1145/3803633.3803666 · Cited by 2
A survey on fake review detection: From pre-trained language models to large language models
Yang, F., Chen, H., Yu, X., Zhang, M., Xiao, X., & Deng, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104715
AGWAN, S., Tambe, A., Shah, S., & Pole, G. S. (2026) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-026-05091-6
“…empirical trends reported across recent studies, identifying strengths and limitations of each paradigm and highlighting recurring reliability patterns such as evaluator bias (Lin et al. 2024), hallucination sensitivity (Huang et al. 2024), and long-context failure modes (Lu et al. 2024).”
Farrahi, V. (2026) · Journal for the Measurement of Physical Behaviour · doi:10.1123/jmpb.2025-0066
Gu, X., Li, Y., Zhu, B., et al. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113953
He, K., Xiao, Q., Chen, W., Jing, L., Wang, Y., Li, S., Yang, D., Xu, H., Pang, K., Xiao, R., et al. (2026) · Journal of Medical Internet Research · doi:10.2196/92852
“Nevertheless, despite using a clinically oriented quantitative framework that combined first-response scoring with composite consistency weighting, the inherent probabilistic nature of LLM outputs cannot be eliminated [43,58].”
Self-citationChen, R., Lin, S., Shao, Z., et al. (2026) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2026-99-0756
Hemal, M. M., Akter, F., Mollah, M. S. H., Kader, M. N., Aurpa, T. T., Sheikh, R., & Hasan, S. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.102186 · Cited by 1
Mamaev, B. (2026) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-80592-655-920261010
Attention-Driven Keyword Extraction for Conversational Retrieval-Augmented Generation
Zhao, L., & Huang, D. (2026) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3804601.3804655
Zheng, X., Chen, T. X., & Zhang, W. (2026) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2026.05.001
Xiao, Y., Xu, D., Li, S., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6778404
Esina, S. V., & Inkpen, D. Z. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-20322-9_27
Multimodal Fusion with External Knowledge (MFEK)
Lin, Z., & Li, Q. (2026) · Wireless networks · doi:10.1007/978-3-032-20416-5_3
Fragoso, A. T. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-15812-3_5
Arous, I., Chehbouni, K., Cheng, Z., & Dossou, B. F. P. (2026) · Springer eBooks · doi:10.1007/978-981-95-3658-0_85
Auditing Hallucination in Lightweight Vision-Language Models for Radiology Captioning
Wang, Z., Zhang, H., Xie, C., et al. (2026) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1109/gaiis69281.2026.11519346
“Hallucination, broadly defined as output content not faithfully grounded in the input or reference evidence, remains a persistent failure mode in generative models [5], [6].”
O cto S elector : Efficient and Effective Batch-Aware Model Selection for Large Language Models
Zhang, G., Lin, Y., & Mehrotra, S. (2026) · Proceedings of the ACM on Management of Data · doi:10.1145/3802095 · Cited by 2
Language Models in Veterinary Clinical Practice
Bollig, N., Lustgarten, J. L., & Venit, E. L. (2026) · Veterinary Clinics of North America Small Animal Practice · doi:10.1016/j.cvsm.2026.03.014 · Cited by 2
EvasionEval: A Benchmark for LLMs in Evaluating Advanced Defense Evasion Techniques
Wang, B., Huang, Y., Li, X., Yu, J., & Zhang, X. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-23450-6_20
Chen, J., & Yu, G. (2026) · International Conference on Educational and Information Technology · doi:10.1109/iceit68991.2026.11521664
“Widespread “Knowledge Hallucinations”: When LLMs encounter knowledge gaps or problems requiring multi-step reasoning, they tend to generate logically incoherent or factually incorrect answers [15], which mislead students at the learning stage [10].”
Zhang, J., Guo, P., Jiang, G., Zhou, M., Wei, G., & Ni, T. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.16.720484
A Hybrid LLM-Based Architecture for Reliable Standardization of Heterogeneous Grant Information
Strykowski, S., Leszczyński, C., Kumor, S., & Śliwicki, M. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-26363-6_19
Retrieval Augmented Generation with Iterative Critique: A Framework for Structured Task Solving
Mezzina, A., Naso, L., & Pavone, M. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21811-7_13 · Cited by 1
Bautista, C. I. D., Domingo, A. N., Monteon, J. P. B. R., & Comia, L. V. (2026) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa68262.2026.11517829
“Empirical research indicates that hallucination rates in legal question-answering tasks can range between 58% and 88%, depending on the model and task configuration [4].”
Error analysis of large language model-generated film subtitles using the FAR model
Chuqiao, L., & Ghassemiazghandi, M. (2026) · Cogent Arts and Humanities · doi:10.1080/23311983.2026.2668253
APLE: A Framework for Adaptable and Personalized Live Explainability for Recommender Systems
Patro, G. K., Mukhopadhyay, S., Banerjee, A., Abreu, D., Perkins, K., Kotwal, S., Sivakumaran, V. N., Bidzyan, A., & Nayak, D. (2026) · ACM Web Science Conference (WebSci) · doi:10.1145/3795766.3799741
Think Before You Leap: A Robot Task Planning Method By LLM
Yang, Z., & Zheng, Z. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522632
“• Error Correction: Identifies and fixes mistakes in the original sequence, mitigating potential logical flaws inherent to the LLM [17].”
Adnan, M., Ali, K., Shamim, M., & Sarwar, N. (2026) · International Conference on Emerging Computational Intelligence (ICECI) · doi:10.1109/iceci69159.2026.11519426
“Huang et al. [2] offer an extensive taxonomy that differentiates factual hallucinations (characterized by contradictions with verifiable facts and fabrication) from faithfulness hallucinations (marked by divergence from input and logical inconsistency).”
MolJury: A Role-Driven Multi-agent Architecture for Factual Molecular Understanding
Zhang, Y., Li, X., Peng, N., Liu, Y., Lu, X., Li, M., Zhou, Y., & Ma, P. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7141-3_31
Loia, V., Orciuoli, F., Peduto, A., & Herrera‐Viedma, E. (2026) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2026.3693564
“RAG improves factual accuracy and epistemic robustness by grounding generated feedback in domain-relevant knowledge, acting as a mitigation mechanism against hallucinations rather than a strict guarantee [24], [25].”
RT-K: A key point-aware transformer framework for efficient vision-language robot control
Li, L., Zhao, S., Jing, H., Zhang, Q., Ju, H., Sun, K., Zhao, J., & Zhu, Y. (2026) · Biomimetic Intelligence and Robotics · doi:10.1016/j.birob.2026.100341
Transforming Privacy Artifacts Into Accessible Reports for Non-Technical Stakeholders
Pfister, Z., Sauerwein, C., Dornauer, B., Mersch, T., Wolf, C., Breu, R., & Vierhauser, M. (2026) · IEEE International Requirements Engineering Conference (RE) · doi:10.1109/re68928.2026.00045
“However, LLMs often act as black boxes, lacking transparency (e.g., through hallucinations) and control-lability, especially in complex tasks [30].”
Lee, G., Kim, S., Byun, Y., Lee, J., & Choi, H. (2026) · International Journal of Precision Engineering and Manufacturing-Green Technology · doi:10.1007/s40684-026-00890-w · Cited by 4
“In their survey, Huang et al. analyzed the root causes of LLM hallu - cination from three perspectives, namely data, training, and inference [26 ].”
InfluentialYu, Q., Zhang, J., & Wu, C. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-23453-7_8
Improving Quantized Model Performance in Qualitative Analysis with Multi-pass Prompt Verification
Adeseye, A., Isoaho, J., & Adeseye, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32732-1_7
Rui, J., Qin, L., & Cai, C. (2026) · Journal of Urban Mobility · doi:10.1016/j.urbmob.2026.100230
How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
He, Z., Kim, H., Zhang, D., & Junior, E. R. H. (2026) · ACM Conference on AI and Agentic Systems (CAIS) · doi:10.1145/3786335.3813144 · Cited by 4
AskSafely: Privacy-Aware LLM Query Generation for Knowledge Graphs
Tosi, M. D. L., & Cabot, J. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-26836-5_4 · Cited by 1
Cross-sectional analysis of large language models in current natural language generation challenges
Maestre, M. M., Martínez-Murillo, I., Martínez, A. M., & Lloret, E. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104922 · Cited by 1
Nananukul, N., & Kejriwal, M. (2026) · ACM Conference on AI and Agentic Systems (CAIS) · doi:10.1145/3786335.3813224 · Cited by 4
Carmichael, A. F. B., Pate, L. A., Duncan, A. J., et al. (2026) · Veterinary Record Open · doi:10.1002/vro2.70035
Heckmann, N. S., Papoutsi, D. G., Barbieri, M. A., Battini, V., Molgaard, S. N., Schmidt, S. O., Melskens, L., & Sessa, M. (2026) · Pharmaceutical Research · doi:10.1007/s11095-026-04121-4 · Cited by 4
“Biomedical LLMs instead, are trained on biomedical literature and therefore less exposed to misinformation or over-general linguistic associations [24, 33].”
Gillis, T. B., Stacy, R., Brumer, S., & Black, E. (2026) · ACM Symposium on Computer Science and Law (CSLAW) · doi:10.1145/3788646.3789525
AI as an Epistemic Technology: Navigating Ethics in Practice in Cases of Distributed Decision Making
Maslen, S., & Hayes, J. (2026) · Springer eBooks · doi:10.1007/978-3-032-20002-0_12
FedDBA: Federated learning based image classification algorithm with local bias-contrastive learning
Ye, J., Hu, H., & Liang, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134087
Zou, H., & Wang, Y. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109178
Decoding causal m6A: a bioinformatics roadmap for psychiatric disorders
Liu, S., Zhao, X., Wei, Z. C., Carr, D. F., & Moraros, J. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag251 · Cited by 1
“Furthermore, underlying LLMs can produce “hallucinations”, creating plausible yet factually incorrect relationships [ 156].”
SciLong2LongEval: Evaluating Large Language Models for Long-to-Long Scientific Text Generation
To, H. Q., Liu, M., & Huang, G. (2026) · ICON · doi:10.1109/icnlp69856.2026.11527736
“While models like GPT-3 [3] can produce fluent outputs, they often degenerate into repetition [7], [8] or introduce hallucinations in extended writing [9].”
A Multi-Model Approach to Mitigate Hallucinations in Large Language Models
Singh, P., Ghosh, A., Ghosh, D., Pramanik, S., Kumari, A., Das, S., & Poddar, V. (2026) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom70271.2026.11526014
“Tonmoy et al. provide a comprehensive taxonomy of mitigation strategies, e.g., prompt engineering and fine-tuning, but, importantly, observe there is no universal evaluation framework for assessing their effectiveness [5].”
Tree-GRPO: A Tree-Structured RAG Reasoning Framework via Group Relative Policy OptimizationPreprint
Ying, Y., Wang, H., & Li, X. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6833494
Self-citationDreyer, M. (2026) · Information - Wissenschaft & Praxis · doi:10.1515/iwp-2026-3008
A hybrid intelligence approach for assessing packaging sustainability claims in e-commerce
Lorkiewicz, W. A., & Wasilewski, A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115504
Alsaleh, O. I. (2026) · Telecommunication Systems · doi:10.1007/s11235-026-01462-8
Dreyer, M. (2026) · Information - Wissenschaft & Praxis · doi:10.1515/iwp-2026-3007
BODNAR, D., & Koldovskyy, V. (2026) · Advances in Cyber-Physical Systems · doi:10.23939/acps2026.01.012
Hybrid Supervised Fine-Tuning Method for Medical Language Models via Explicit Reasoning Modeling
Wang, X., Wei, T., Nan, Z., & Wan, S. (2026) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-026-2929-6
“However, small-parameter models typically suffer from limited medical knowledge coverage and weaker multi-step reasoning, and thus are prone to unreliable inferences and factual errors [9] .”
Hua, Z., Wu, K., Ru, C., Luo, Y., Wang, M., Yu, M., & Han, Y. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-7299-1_31 · Cited by 1
No Time, No Money for Research? Some Pragmatic Advice for Productive and Sustainable Publishing
Lim, W. M., & Manrai, A. K. (2026) · Journal of Global Marketing · doi:10.1080/08911762.2026.2671579
“Nonetheless, such promise requires caution, since hallucination remains a live problem in large language models (Huang et al., 2025), uncritical use of artificial intelligence in qualitative analysis can weaken sensitivity to context, ambiguity, reflexivity, and power (Friedman et al., 2025), and…”
OptoChat: a large language model with retrieval augmented generation for optics
Bao, X., Wang, H., Chen, S., Zhang, Y., Chen, W., Di, K., Lv, M., zhao, M., Wang, G., Zhao, W. Z., et al. (2026) · Journal of Physics Photonics · doi:10.1088/2515-7647/ae7491
Self-citationAutomating the qualitative interview? Using Gen AI chatbots in social science research
Jack, T., Cooper, A., & Flower, L. (2026) · Methodological Innovations · doi:10.1177/20597991261448157 · Cited by 5
“The tendency of LLMs to “hallucinate” content remains an open problem, which presents serious risks to the AI-assisted researcher (Farquhar et al., 2024; Huang et al., 2025).”
ReGA: Zero-Overhead Graph Alignment for Structural Hallucination Detection Without Generation
Noël, V., & Seidou, E. Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774905.3794657
Courchaine, C., Sethi, R. J., & Qiu, H. (2026) · ACM Web Conference (WWW) · doi:10.1145/3774905.3793124
“This kind of metacognitive framework is crucial for addressing LLMs’ inability to assess their own uncertainty [10] and their tendency to systematically generate hallucinated content [5].”
VikingMem: A Memory Base Management System for Stateful LLM-Based Applications
Fu, J., Chen, J., Wang, M., He, A., Sheng, M., Ke, X., Zhu, Y., & Gao, Y. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3827998.3828037 · Cited by 6
Li, R., Chen, C. E., Li, X., Zhang, H., Wang, T., & Cheng, L. (2026) · Journal of Engineering Design · doi:10.1080/09544828.2026.2680617 · Cited by 3
Sakharkar, M., Jalihal, P., Chang, S., Patel, P. N., Chavez, M. M., & Levi, J. R. (2026) · Otolaryngology · doi:10.1002/ohn.70309 · Cited by 1
“6,7 While LLMs are clearly powerful tools, there are signi fi cant ethical concerns we must consider.”
Descriptor: Electronic Device Domain Factoid Question-Answering Dataset (ElecDevQA)
Huang, B.-W. (2026) · IEEE data descriptions. · doi:10.1109/ieeedata.2026.3698414
“While they can provide general answers to domain-specific questions, their ability to generate factually correct text remains a challenge [1].”
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.