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 1,701–1,800 of 2,245
EntiTractor: entity extraction for coherent hallucination correction in paragraph-level text
Yao, J., Yao, J., Zang, W., Zhao, K., Zhang, H. M., & Wang, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133359
Synthesis‐GPT: An Intelligent Assistant for Solid‐State Electrolyte Synthesis
Li, B. R., Li, P. H., Zhong, Y., Yan, Z., Yu, Z., Ning, Z., Ouyang, C., Chen, X., Jin, H., Yang, L., et al. (2026) · Small Structures · doi:10.1002/sstr.70448 · Cited by 1
“Those models lack robust domain grounding and are unreliable for specialized reasoning without expert verification [24, 27, 31].”
Qu, Q., Gao, J., Guo, F., Duffy, V. G., & Man, S. S. (2026) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2026.103996
Navigating maritime emergencies with large models: A lifecycle-oriented review
Xu, J., Yang, Q., Yang, Z., Gao, Y., Yang, K., & Jiang, J. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115411 · Cited by 2
IILAP+: Exploring AI-Assisted Dataset Creation for Critical Thinking Assessment
Nurbakova, D., & Магдановна, Е. Л. (2026) · ACM Conference on Learning @ Scale (L@S) · doi:10.1145/3774398.3811569
BioBrain: A Multi-Agent Framework for Natural Language Driven Quantitative Microscopy Data AnalysisPreprint
Tsolakidis, K., Breuer, A., Bender, S. W. B., Margaritaki, S., Dreisler, M. W., Oikonomou, A., & Hatzakis, N. S. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.17.732700
“Direct use of frontier language models generated plausible but quantitatively incorrect analyses without explicit failure 27 , whereas BioBrain constrained reasoning to validated analytical methods and deterministic tool execution.”
LLM-Enabled Multi-Agent Collaborative Instrument Control for Automated Microelectronic Testing
Zhang, Y., Liu, J., Zhang, Z., qi, L., Wang, P., Wang, X., & Zhao, W. S. (2026) · Advanced Devices & Instrumentation · doi:10.34133/adi.0202 · Cited by 2
Advancing Regulation in Artificial Intelligence: An Auction-Based Approach
Bornstein, M., Che, Z., Julapalli, S., Mohamed, A., Bedi, A. S., & Huang, F. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812397 · Cited by 2
Memari, M., Rudolph, G., Burns, B., Howlett, E., Bramwell, C., & Mcewan, G. (2026) · Intermountain Engineering, Technology and Computing (IETC) · doi:10.1109/ietc69527.2026.11568649
“Huang et al. [10] present a detailed taxonomy distinguishing factuality hallucination from faithfulness hallucination and survey detection and mitigation strategies.”
Legitimate: Resurrecting Biased Ontologies On the Path to Superintelligence
Monroe‐White, T., White, K., & Hashmi, N. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3806757
LearnForge: An AI-Powered Intelligent Learning Assistant with RAG-Based Document Intelligence
Nitishkumar, R. J., & Ranjini, R. (2026) · International Conference on Intelligent Systems and Computational Networks (ICISCN) · doi:10.1109/iciscn67954.2026.11566245
“Large Language Models (LLMs) have demonstrated strong capabilities in text generation and question answering; however, comprehensive surveys have documented their tendency to produce factually incorrect or fabricated information, a phenomenon widely termed hallucination [15].”
Wilkinson, B. D., & Brown, A. M. (2026) · The Journal of Humanistic Counseling · doi:10.1002/johc.70048
Distribution-Aware Diffusion-LLM for Robust Ultra-Long-Term Time Series Forecasting
Ghosh, F., Hashemi, V., & Kainz, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38410-2_37
What Older Adults Need from Digital Loneliness Support: A Mixed-Methods Requirements StudyPreprint
Zhao, J., & Or, C. K. (2026) · Research Square · doi:10.21203/rs.3.rs-9991723/v1
An Intelligent Fault Diagnosis Agent based on Knowledge Graph For High-speed Train
Yao, Y., Wang, H., Sun, P., Zhang, J., Li, W., & Ren, L. (2026) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/icaisisas68969.2026.11567864
“This phenomenon is also usually mentioned as LLM ‘ hallucination ’ [13], which is unacceptable for the industrial systems that often related to large amounts of property and even many human lives.”
Self-citationPIDAgent: PID Tuning Via LLM Agents and RAG
Chen, Y., Su, H., & Zhu, Y. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11560610
“Although they can formulate conceptual strategies, their inability to autonomously interface with external APIs or physical infrastructures without supporting frameworks severely limits their practical utility in interactive tasks [5].”
NBI-RAG: A Layout-Aware and Localized Question Answering System for Nuclear Fusion Facilities
Zhang, Q., Xie, Y. D., ZHAO, Y., Cui, Q. L., & Gu, Y. (2026) · International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) · doi:10.1109/aiita69518.2026.11567237
“While General Large Language Models (LLMs) possess strong semantic understanding capabilities [7], their lack of private domain knowledge in nuclear fusion leads to high hallucination rates [8] when processing vertical scenarios.”
Li, J., Chen, L., & Chen, Z. (2026) · International Conference on Sensor-Cloud and Edge Computing System (SCECS) · doi:10.1109/scecs69812.2026.11565843
“Despite recent progress, large language models (LLMs) remain vulnerable to hallucination and temporal knowledge gaps [1].”
Ma, Z., Li, J., Wen, Y., & Yu, H. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116512 · Cited by 1
AgentCite: Task-Isolated Multi-Agent Collaboration for Cost-Effective Long-Context Citations
Cao, Z., Wang, H., Jin, L., Zhu, T., & Ren, L. (2026) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/icaisisas68969.2026.11567713
“This positional bias, coupled with the inherent generative nature of LLMs, inevitably exacerbates the hallucination problem— where models fabricate unverified content [6], [10].”
Self-citationHo, T. K., Luo, L., Liu, Z., Wang, H., & Chen, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1947-6_7
Self-citationLiu, C., Yang, C., & Ma, J. (2026) · International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) · doi:10.1109/aiita69518.2026.11567142
Two-stage distributionally robust decoding for reliability-oriented natural language generation
He, G., La, L., Gao, K., & Zheng, J. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105000
Кравчук, О. А., Taranowski, A. O., Sinko, D., Kravtsov, H., & Samoylov, V. D. (2026) · Nuclear and Radiation Safety · doi:10.32918/nrs.2026.2(110).07
Leveraging AI Flaws for Human Learning
Sinha, T. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-29791-4_32
Wrenn, J. O., Behrens, M., Hershey, S., Maldaver, M., Mitchell, J., Thompson, T. J., Triana, A. J., Virk, Z. M., Akdas, Y., Cauley, M. R., et al. (2026) · Journal of Medical Internet Research · doi:10.2196/88834
“However, there are strategies for mitigation of LLM hallucinations that were not within the scope of this project [17].”
Chen, W. (2026) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2026.103095
Pragmatic cohabitation: how Türkiye’s digital publics negotiate the meaning of generative AI
Yıldızgörür, M. R., & Salman, G. (2026) · AI & Society · doi:10.1007/s00146-026-03199-z
Alonso-Robisco, A., Carbó, J. M., García, C. J., Quintana, J., & Tarancón, J. (2026) · Documento ocasional/Documento ocasional - Banco de España · doi:10.53479/43986
“Prior research highlights several risks associated with their deployment in accounting contexts, including hallucinated content, lack of transparency, and the risk of overreliance on automated outputs (Bommasani et al., 2021; Vasarhelyi et al., 2023; Street and Wilck 2023; Huang et al. 2024).”
An empirical study of LLM-based refactoring consistency
Zhang, Y., Yuan, L., & Dong, C. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10911-6 · Cited by 3
“However, current studies focus on exploring LLMs’ capabilities in assisting code refactoring (DePalma et al. 2024), and LLMs’ hallucination poses potential risks to consistency before and after refactoring (Huang et al. 2025; Zhang et al. 2025c).”
Knowledge representation evolution: From knowledge graphs to knowledge augmentation
Wang, H., & Wang, M. Y. (2026) · Journal of Terminology and Knowledge Engineering · doi:10.3724/jtke-20260001
Self-citationPeng, X., Rao, G.-Z., Zhang, J.-H., & Zhang, L. (2026) · Expert systems with applications · doi:10.1016/j.eswa.2026.133433
A Framework for LLM Integration in Secondary Education: Insights from Computing Teachers
Reichert, H., Yasir, T., Satyavolu, M., & Barnes, T. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29763-1_8 · Cited by 1
Bhat, S., & Varma, V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29763-1_18
Martinenghi, A., Guidotti, S., Donabauer, G., Koyutürk, C., Ortiz-Beltrán, A., Theophilou, E., Chimisso, R., Bink, M., Garzotto, F., Taibi, D., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29763-1_29 · Cited by 1
TAVR-VLM: Risk-Conditioned Causal Grounding for Hallucination-Resistant Report Generation
Lu, Z., Liu, X., Song, S., Ji, C., Nguyen, A., Su, J., Razzak, I., & Wang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38059-3_57
Chopra, J. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-29237-7_38
Dhanorkar, S., Passi, S., & Vorvoreanu, M. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812402 · Cited by 32
Xiao, K., Yang, L. T., Tulajiang, P., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7023469
Chen, X., Wang, Q., Wang, S. Q., Zhang, W., Liu, Y., Liu, B. F., & Jiang, Z. H. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3808099
Validating LLM-Generated SQL Queries through Metamorphic Prompting
Lin, L. G., Zhu, Q., Hong, J., Wang, C., Liu, Y., & Wu, R. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3797146 · Cited by 1
Peng, C., Jiang, M., Zhou, Y., & Wu, L. (2026) · Proceedings of the ACM on Software Engineering · doi:10.1145/3808141
Cao, X., Li, J., Ying, T., & Liu, Z. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105028 · Cited by 3
A Security Closed Loop-based Framework for Addressing Security Challenges in 6G Networks
Ruta, M., Pérez, A. G., Cailliot, L., Giardina, P. G., Valero, J. M. J., Pérez, M. G., Ayed, D., & Landi, G. (2026) · Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) · doi:10.1109/eucnc/6gsummit68295.2026.11577395
“While the generative AI modules significantly accelerate CACAO playbook generation, LLM hallucinations still pose a risk to operational reliability [31].”
Zheng, L., Lu, Y., & Han, Y. (2026) · Journal of Engineering Education · doi:10.1002/jee.70073
LOCARD: An Agentic Framework for Blockchain Forensics
Yu, X., & Knottenbelt, W. J. (2026) · IEEE International Conference on Blockchain and Cryptocurrency (ICBC) · doi:10.1109/icbc67748.2026.11575479 · Cited by 5
“Large Language Models (LLMs) notoriously suffer from hallucinations and reasoning inconsistencies [20], [21].”
PromptFishing: Active Hallucination Inducement to Distinguish LLMs From Humans
Chen, B., Li, G., Wu, J., Li, J., & Fang, H. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3709099
“LLMs are prone to hallucinations, i.e., confidently generating factually incorrect or nonsensical content despite high linguistic fluency [28], [29].”
白明和, Chen, W., Li, S., & Zhu, J. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner67736.2026.00072
“However, their reliability in practical applications is often hindered by hallucinations and overconfidence in erroneous reasoning [14], [15].”
An artificial intelligence framework for transforming unstructured text into structured survey data
Manzi, G., Guo, Q., Russo, L., & Grané, A. (2026) · Decision Analytics Journal · doi:10.1016/j.dajour.2026.100730
Sun, Y., & Sun, J. (2026) · ACM Interactive Health Conference · doi:10.1145/3786579.3804942
"I Use ChatGPT to Humanize My Words": Affordances and Risks of ChatGPT to Autistic Users
Ma, R., Zhang, Z., Chen, C., Yang, F., Huang, X., Wu, H., & Li, L. (2026) · ACM Interactive Health Conference · doi:10.1145/3786579.3804943 · Cited by 3
Sui, Y., Li, C., Zhang, L., Song, D., & Liu, H. (2026) · ACM Transactions on Information Systems · doi:10.1145/3827609
Shen, Y., Chen, Y., Li, M., Gu, X., & Zhuang, A. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1885204
Wong, K. K. L., Tu, J., Jiang, S., et al. (2026) · npj Heritage Science · doi:10.1038/s40494-026-02770-7
“This task demands robust cross-modal reasoning, veri fi cation of structural – semantic coherence, and reliable detection of misalignment, hallucination, or incorrect variant pairing 36 .”
Chen, S., Xiong, L., Chow, M., & Tang, Y. (2026) · Cyber-Physical Energy Systems · doi:10.1016/j.cpes.2026.04.003 · Cited by 2
Jafaraghaeian, D., & Butvilas, T. (2026) · Applied Business Issues & Solutions · doi:10.57005/ab.2026.2.9
Mitigating hallucination in Multimodal Large Language Models via cross-layer visual anchors
yang, C., Cai, S., Yuan, J., & Hu, C. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114380 · Cited by 2
Basu, S., Ravi, S., Roy, A., Kumari, A., & Shashi Kumar, M. (2026) · Medical Journal Armed Forces India · doi:10.1016/j.mjafi.2026.06.002 · Cited by 1
A Dual-source Fusion Enhancement method for Question Answering on Acute Mountain Sickness
Sui, M., Bi, X., Yu, G., Zhang, L. H., Xu, H., & Zhao, K. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582261
“Furthermore, hallucinations and outdated information remain critical obstacles for LLM deployment in medicine [6].”
Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
Xie, Z., & Sun, Z. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582530 · Cited by 4
“However, their reliance on parametric knowledge introduces a critical challenge: hallucination, where the generated content deviates from factual correctness [3], [4].”
Human-in-the-Loop Framework for Hallucination Mitigation: A Controlled Comparison of GPT and LLaMA
Kai, J. N. J., Syahidi, A. A., & Kiong, K. B. (2026) · International Conference on Business and Industrial Research (ICBIR) · doi:10.1109/icbir69932.2026.11584794
“Collectively, this line of work reflects a shift toward cost-aware hallucination mitigation, emphasizing adaptive inference strategies that trade additional computation for reduced human effort [9], [25].”
Cui, W., Hu, Y., Liu, Z., Feng, J., Zhang, S., & Wen, Y. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-22545-0_7
LLM-Based Dual-Pipeline Extraction of IoCs and TTPs from Backdoor CTI Reports
Liu, B. F., Jiang, Z. H., Chen, L., Liu, Y., Wang, Q., Li, Y., Yao, Y., & Wang, S. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582506
“Regarding the specific problem of extracting threat knowledge from CTI reports, there is a growing body of work focused on IoCs and TTPs extraction using LLMs [4]-[10].”
DCHD: Density clustering-based hallucination detection in large language models
Chen, J., Wu, Q., Du, K., Jiang, W., Wang, C., Gu, K., & Du, X. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116607
Kostka, A., & Chudziak, J. A. (2026) · Knowledge · doi:10.3390/knowledge6030017
“While Retrieval-Augmented Generation (RAG) is an effective tool for grounding, research indicates that retrieval by itself is not a complete solution [7].”
Streamfeed: AI-Mediated Feedback Reflection for Live Streamers
Mallari, K., Kute, S., McCarthy, B., & Zachry, M. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31418-5_4
Chen, J. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581584
“However, the dominant prompt-based paradigm is often computationally costly and suffers from unreliability (i.e., ”hallucination”) [10], rendering it unsuitable for high-stakes safety applications, creating a need for more efficient adaptation methods.”
Sarcina, F. P., & Baldassarre, M. (2026) · Community Notebook People Education and Welfare in the Society 5 0 · doi:10.61007/qdc.2026.1.407
KGtelescope: Knowledge Graph Guided Model Routing for Factual Question AnsweringPreprint
Spahiu, B., Maccarini, M., Rula, A., & Palmonari, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7067175
Radar Algorithm Generation System Based on Domain-Adaptive Retrieval-Augmented Generation
Hu, L., Jia, Y., Zhao, B., Xie, M., Li, Y., & Dong, K. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582809
Zare, A., & Assal, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29723-5_35
“However, using LLMs in software development has its challenges, as they can hallucinate [24] ( e.g., suggest non-existent libraries) or suggest insecure code [33].”
Proactive Robots in Human–Robot Action Teams
Jamshad, R., Simkins, S., & Riek, L. D. (2026) · Emerald Group Publishing Limited eBooks · doi:10.1108/s1534-085620260000021020
Panjanani, K., Sharma, V., Sharma, S., et al. (2026) · IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT) · doi:10.1109/ic2pct68894.2026.11584301
“Moreover, uncontrolled retrieval generative models are prone to hallucination and provide legally inaccurate results [7].”
SPARQ: Graph-Structured Queries Drive GNN Retrieval for Knowledge Graph Question Answering
Wang, M. Y., Wang, X., Liu, R., Li, Y. Z., & Luo, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2494-4_9
Shi, J., Yue, X., Liu, W., Chen, Y., Dong, F., & Li, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2480-7_9
Vlahović, I., Biškupić, I. O., & Balković, M. (2026) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro70003.2026.11591632
“According to literature [8, 9] , hallucination is defined as the generation of plausible yet nonfactual content.”
InfluentialMOD2SAD: enhancing malicious office document detection through semantic-aware deobfuscation
Leng, T., Liao, T., & Yuan, B. (2026) · Scientific Reports · doi:10.1038/s41598-026-60598-4
Davis, M., Chow, C. M., & Divekar, R. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30781-1_22
A Multi-agent Framework for Factuality Hallucination Detection Using Complex Knowledge Graph
Minh, L. X., Khuong, H. N. D., Minh, N. H., Nhut, N. M., Phat, T. L., Vinh, N. N., An, T. C., Tuyen, B. T. T., Quan, T. T., & Hua, T. P. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2480-7_10
Gjurčević, J., & Kolar, P. (2026) · MIPRO ICT and Electronics Convention (MIPRO) · doi:10.1109/mipro70003.2026.11591973
“These are plausible but incorrect outputs generated by LLMs, which pose risks in software development and technical domains [5], [12].”
Meaning-Making and Human Flourishing as an Analytic Lens for Social Media, Games, and AI
Kapadia, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30781-1_37
When structure predicts hallucination: Aligning LLMs with knowledge graph features
Ali, U., Lynden, S. J., Matono, A., & AMAGASA, T. (2026) · Data & Knowledge Engineering · doi:10.1016/j.datak.2026.102630 · Cited by 1
Yang, Y., Feng, H., Lu, B., & Sun, J. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-30826-9_26
Drašković, N., Rešetar, M., & Vejzagić, V. (2026) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro70003.2026.11591963 · Cited by 1
“These perspectives align with documented GenAI failure modes – including hallucinations [26] and systematic response biases such as order effects and social desirability patterns [27], [28], and therefore motivate governance and verification mechanisms as theoretically relevant antecedents of…”
InfluentialWang, C., Li, C., Wang, P., Zhang, L., Liu, S., 祁吉, Hu, J., Cai, Y., Zhao, H., & Pu, R. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104997 · Cited by 2
Evaluating Attention Patterns of LLMs Using Adversarial Reading Comprehension
Encinas, R. J. O., & Laguna, A. F. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-20897-2_59
Zhu, Y., Zhang, B., Gong, M., Wang, G., Xiong, B., & Xie, C. (2026) · 中国科学基金 · doi:10.3724/bnsfc-2025-0267 · Cited by 1
Adaptive DoLA-Enhanced LVLM for Power Safety Violation Detection
Wen, T., Wang, Y., Tan, Y., Zhang, G., & Mo, W. (2026) · IEEE International Conference on Electrical Power Systems and Intelligent Control (EPSIC) · doi:10.1109/epsic70071.2026.11590211
“Nevertheless, LVLMs are prone to “hallucinations,” where generated text contradicts the image content or introduces nonexistent objects or attributes [8], [9].”
From Chatbots to Chemists: Autonomous Agents for Heterogeneous Catalysis
Jin, M., Liao, C., Xu, Z., Song, Y., He, R., Zhang, Y., Hu, X., & Shen, Z. (2026) · ACS Catalysis · doi:10.1021/acscatal.6c02268 · Cited by 4
A region representation for entity tagging and locating
Hu, Y., Chen, Y., Wen, X., & Xu, Y. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104605
Qi, P., Zhao, Y., Hsu, W., & Lee, M. L. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809601
Failing Forward: Understanding Query Failure in Retrieval, Judgment, and Generation
Hosseini, S. M. B., Arabzadeh, N., Saliminabi, M. H., Androutsos, D., Zihayat, M., & Bagheri, E. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809859 · Cited by 1
Zhou, Z., He, Y., Guo, Y., Yu, H., Fang, L., & Li, F. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809572
From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation
Lu, Z., Sang, L., Mu, L., & Zhang, Y. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809563 · Cited by 3
Solà, P. F., Molina, A., & Lladós, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36039-7_15
Zhang, D., & Smucker, M. D. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809973 · Cited by 1
Reconstruction of Translator Co-Subjectivity and Translation Teaching Innovation in the GenAI Era
郎, 柯. (2026) · Modern Linguistics · doi:10.12677/ml.2026.147635
Syahidi, A. A., Nuchitprasitchai, S., & Viriyapant, K. (2026) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse68839.2026.11596890
“Hallucination in language models remains a critical challenge in building reliable generative systems [12], referring to fluent but factually incorrect or unsupported outputs [5], [13], [14].”
Cuarto, P. M. (2026) · Research Square · doi:10.21203/rs.3.rs-10300970/v1
Hallucination-Hunting Season, or UX Interventions To Better Read LLM Outputs
Belfiore, D., Іщенко, В., & Detyniecki, M. (2026) · Annual Symposium on Human-Computer Interaction for Work (CHIWORK) · doi:10.1145/3805029.3818292
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.