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 1,301–1,400 of 2,245
Yue, F., Zhang, Y., Liu, Y., & Yu, Y. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105938 · Cited by 1
How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
Huang, W., Bi, K., Cai, Y., Chen, W., Guo, J., & Cheng, X. (2026) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3773966.3777988 · Cited by 3
Zong, R., Zhang, Y., Yue, Z., & Wang, D. (2026) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3773966.3777996
Genetic Ancestry and Cancer Genomics: An LLM-Based Framework for Equitable Precision Oncology
Satrawada, J., & Satravada, B. A. (2025) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon67554.2025.11378509
Ghosh, A. K., Fattahi, S., Kogawara, Y., Azarhoushang, B., Okamoto, T., & Ura, S. (2026) · Research Square · doi:10.21203/rs.3.rs-8872511/v1
A Hybrid SQL-RAG-LLM Question Answering System for Plastic Waste Management
Sivan, D., Wei, Y.-L., Kumar, K. S., Chen, Y.-J., & Jose, R. (2025) · International Conference on Interdisciplinary Computer Science and Engineering (ICICSE) · doi:10.1109/icicse67247.2025.11390794
“However they could also generate non-factual content (known as hallucinations), especially when asked to produce quantitative claims without explicit grounding [14, 15].”
Knowledge-Grounded RAG for Diagnosing Spleen-Stomach Disorders in TCM
Lin, W., Xing, B., Liu, X., & Xie, Y. (2025) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbdai66607.2025.11388485
“…remarkable capabilities in general medical question-answering, their direct application to TCM frequently results in hallucinated syndromes, logically inconsistent prescriptions, or generic, non-actionable advice — outcomes that are not only clinically useless but potentially harmful [3].”
Interpreting LLMs: challenges to a knowledge-first approach
Al-Khalfa, A. (2026) · Inquiry · doi:10.1080/0020174x.2026.2626969
Chung, J., Lee, M., & Kim, J. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11387844
“At the same time, prompt sensitivity, hallucination errors, domain adaptation limitations, latency in real-time systems, and safety concerns create additional hurdles for robust and trustworthy adoption [7], [8].”
Research on the Method of Factual Hallucination Relief Based on blockchain Large Language Model
Li, P., Yang, Y., Zhang, J., & Cheng, S. (2025) · International Conference on Blockchain Technology and Information Security (ICBCTIS) · doi:10.1109/icbctis66509.2025.11387485
“The illusion of big language model can be divided into two categories: illusion of fact (external illusion) and illusion of loyalty (internal illusion)[12].”
Can LLMs Aid Expert Elicitation for Causal Modeling?
Shaposhnyk, O. A., Zahorska, D., & Yanushkevich, S. N. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00306
“Acommon challenge of LLMs is that they are prone to hallucinate [23] and generate text that is irrelevant to the topic.”
Shoumi, M. N., Harada, K., Oshita, H., Sakashita, S., & Inoue, S. (2026) · doi:10.2196/preprints.93374
LieToMe: A Multi-Agent System for Detecting Hallucinations in Large Language Models
Blitti, K. E. K., Tola, F. G., Shukla, M., Ladva, V., & Dholakia, N. H. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-17834-3_29
LLM-VeriOpt: Verification-Guided Reinforcement Learning for LLM-Based Compiler Optimization
Fang, X., Kang, J., Rocha, R. C. O., Ainsworth, S., & Mukhanov, L. (2026) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1109/cgo68049.2026.11395239 · Cited by 5
“In contrast, traditional compilers ensure deterministic equivalence, whereas LLMs are prone to hallucinations [14] that may generate invalid or inconsistent IR and assembly.”
Retrieval-Augmented Generation for Multi-Hop Question Answering Based on Structured Planning
Huang, Y., Yang, L., Yang, X.-H., & Xu, X. (2026) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3789506 · Cited by 4
Junnuthula, S. K. R., & Singh, V. K. (2025) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart66937.2025.11389636 · Cited by 1
Learning by Taking Notes: Memory-Guided Continual Learning for Generative Multimodal Models
Guo, Y., Guo, C., Gao, Y., & Sun, Y. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00456
“In generative VLMs, hallucinations [18, 25] refer to instances where the model produces incorrect, misleading, or non-existent information that is not grounded in the input data.”
Training-free counterfactual hallucination mitigation method for large vision-language models
Li, X., Wang, B., Ju, X., Hu, Y. C., & Wang, W. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02577-3 · Cited by 2
“Recent studies confirm that LVLMs inevitably inherit these statistical biases [ 12 , 39 , 40], which frequently manifest as hallucinated objects in generated answers.”
Tractable Asymmetric Verification for Large Language Models via Deterministic Replicability
Chong, Z., Ohsaki, H., & Kuan, B. N. C. (2025) · IEEE Student Conference on Research and Development (SCOReD) · doi:10.1109/scored68498.2025.11399166 · Cited by 1
“Recent theoretical and empirical work shows that hallucination is an inherent limitation of LLM architectures, unavoidable in both single and multi-agent settings [13], [16], and surveys confirm that this challenge is pervasive across the field [17].”
QEC-LLM: Training Query-focused Extractive Compression Model with LLM-guiding for Open Domain QA
Wang, S., Duan, J., Li, X., Wen, H., Zhang, Y., Liu, C., & Yi, Z. (2025) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec66846.2025.00099
“However, LLMs often struggle with high inference costs and performance degradation from redundant context, especially when dealing with efficiency-sensitive questions [2].”
Domain Knowledge graph enhancement method
Liang, Z., & Lin, W. (2026) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece69169.2026.11399755
“While Large Language Models (LLMs) have demonstrated remarkable performance in various language tasks, their hallu-cination problem has increasingly become a critical challenge [1].”
Hao, K., & Wang, B. (2026) · Digital Medicine · doi:10.1097/dm-2025-00015 · Cited by 4
Beyond Static LLM Policies: Imitation-Enhanced Reinforcement Learning for Recommendation
Zhang, Y., Xie, L., Qiu, R., Liu, J., & Wang, S. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00098 · Cited by 4
“…responses [8], [48], yet relying solely on LLMs necessitates frequent calling of the API, resulting in consistently high latency; (2) outputs are prone to spurious associations and reinforcement of recurrent patterns, under-mining their reliability as standalone recommendation policies [10], [20].”
Ishadya, A. P. D., Withanaarachchi, A. S., & Jayalal, S. (2025) · International Conference on Advances in Technology and Computing (ICATC) · doi:10.1109/icatc68823.2025.11407841 · Cited by 2
“[16]”
Reimagining Reality: Innovations in AI Hallucination Management and Trustworthy Generation
Nag, A., & Chaudhuri, D. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7534-2.ch012 · Cited by 1
ADS: A Math Word Problem Solver Based on LLM Prompt Engineering
Ma, F., Zhang, L., & Chang, X. (2025) · International Symposium on Computer Engineering and Intelligent Communications (ISCEIC) · doi:10.1109/isceic67854.2025.11405681
“However, existing methods still exhibit notable limitations: reasoning steps generated by LLMs may appear plausible but are actually erroneous (a phenomenon known as hallucination) [7], and current decomposition strategies fail to dynamically adapt to problem complexity.”
Automated Reporting for Metrology via Agent-based Distributed ArchitecturePreprint
Albuquerque, Y. F., Beghelli, J. M., & Alves, W. D. S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6312925
Offscript: Agentic Auditing of Instruction Adherence in LLMs
Clark, N., Bai, R., & Mitra, T. (2026) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3786304.3787891
Providers of relief in distress: RAG-based LLMs as situation and intent-aware assistants
Nazar, A. M., Norman, B., Northway, H., Toutoungi, A., Zatkalik, E., Carlson, G., Sabado, E., Shawa, H., & Selim, M. Y. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1712596
“…framework with structured knowledge bases and memory-aware orchestration to provide factually grounded, context-sensitive responses across eight core domains, including medical, legal, food, housing, immigration, and crisis intervention (Lewis et al., 2020; Gao et al., 2023; Huang et al., 2025).”
Detecting and Correcting Hallucinations in Paragraph-Level Text with Ensemble-Based Evaluation
Tripathi, S., & Rathore, H. (2025) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa67132.2025.00077 · Cited by 1
“Other work categorizes types and causes of hallucinations [3], with a primary focus on content creation and detection rather than correction. b) Hallucination Detection Metrics: Methods like FactCC [17], SummaC [18], and SMART [19] automatically detect inconsistencies at the sentence level.”
A Generative AI-Enhanced Hybrid Framework for Reliable Long-Term Photovoltaic Power ForecastingPreprint
Qi, Y., Lou, C., & Yang, J. S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6334387
Green by Design AI in Fashion Retail and the Rise of the Conscious Consumer
Malhi, A. S., Yadav, P. S., Bisht, D., Sharma, A. P. G. K., Sharma, A., & Rashmi, B. H. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5525-2.ch001 · Cited by 1
A Consistency-Oriented Verification Framework for Reliable Power Industry LLMs
Wang, B., Zhang, L., Li, Y., & Guo, N. (2025) · International Conference on Electronic Information Engineering and Computer Communication (EIECC) · doi:10.1109/eiecc67963.2025.11409479
“"Hallucination," defined as the generation of factually incorrect or nonsensical content, is a pervasive issue in generative AI [19].”
Zhang, J., Liu, H., Wengen, L. I., Wen, J., Zhao, Y., Chen, J., Liu, J., & Wu, C. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401937
“…to knowledge-intensive and factually demanding domains like diabetes, these models, trained on general-purpose corpora, reveal two core limitations [8]: a lack of in-depth domain knowledge coverage and the inherent problem of factual hallucinations, both of which are unacceptable in a medical…”
Rectifying illusion: a Buddhist–Confucian framework for LLM hallucinations
Sankaran, S. (2026) · AI and Ethics · doi:10.1007/s43681-026-01053-y
Toward Cost-Efficient Metadata Curation in Agricultural Genomics with LLMs
Liu, Y., Spangler, M., Clarke, J., & Yu, H. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402477
“However, LLM-generated workflows do need verification and refinement since LLMs can be prone to errors or omissions because of hallucinations [16].”
Probing LLM Hallucination from Within: Perturbation-Driven Method via Internal Knowledge
Lee, S., Hsu, H., Chen, C.-F. R., & Chau, D. H. P. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402288 · Cited by 1
“Our categorization refines hallucination types beyond existing work [6], [28] (Sec.”
SHARE-RAG: A Structure-Aware and Hypothesis-Guided Retrieval-AugmentedPreprint
Liu, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6365614
Shrestha, M., & Kim, E. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401920 · Cited by 3
“Since the underlying corpora are uncurated and they often exhibit hallucination,producing fluent but factually incorrect or unverifiable statements [1]–[3].”
Jasem, A. N. A. A. (2026) · International Journal of Research · doi:10.26643/ijr/22
Real-Time Adaptive Topic Modeling Framework for Identifying Social Engineering Attacks
Bhasin, M., Abri, F., Webb, J., & Andreopoulos, W. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402505
“LLMs are also prone to hallucinations [62], a phenomenon in which a model produces incorrect or nonsensical content.”
Maiya, A. S. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00312
“• Hallucination : LLMs can produce confident, fluent output that is factually incorrect or misleading [16].”
Deploying generative AI in business planning assignments
Metzger, M. L., Walker, D. O. H., & Plummer, L. A. (2026) · Nankai Business Review International · doi:10.1108/nbri-10-2025-0149
Wang, Z. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00208
“While richer context reduces overall errors, it may introduce issues like overdesign [6].”
Liu, C., & Chen, J. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02257-2
Perception Uncertainty and Collective Robustness in AI-Driven Swarm UAV SystemsPreprint
Kravchuk, O., Taranowski, A., Sinko, D., Kravtsov, H., & Victor, S. (2026) · Research Square · doi:10.21203/rs.3.rs-9065913/v1
AutoEER: Large Language Model Agent Framework for Automated English Exam Report
Xie, D., Li, X., Xiong, Q., Wang, S., Jiang, Y., Liang, Y., & Jin, A. (2025) · International Academic Exchange Conference on Science and Technology Innovation (IAECST) · doi:10.1109/iaecst68792.2025.11415007
“Single LLMs, due to their inherent limitations, can produce "hallucinations"—seemingly plausible outputs that contradict objective reality [16].”
Representational and Behavioral Stability of Truth in Large Language ModelsPreprint
Dies, S., Maynard, C., Savcisens, G., & Eliassi‐Rad, T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6097886
6G AI Security : from fundamentals to offensive and defensive landscape in 6G
Braeke, A., Deac, D., Nguyen, T. T., Gür, G., Pham, Q., Yapa, C., Naranjo, P. G. V., Mora, H. C., Moremada, C., & Liyanage, M. (2026) · Zürcher Hochschule für Angewandte Wissenschaften digital collection (Zurich University of Applied Sciences) · doi:10.21256/zhaw-35849
Crisis Observatory: Extracting Credible Signals During a Crisis in the Age of LLMs
Lo, K.-C., Maneriker, P., Ganesh, S. S., Winecki, D., Garrett, K., Hyder, A., Nandi, A., Shalin, V. L., Bowen, S. A., Sheth, A., et al. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00333
“However, such models often generate non-factual text, a fundamental liability during a crisis [4], [5].”
TouaRAG - A Context-aware Multi-layer RAG Framework for Personalized and Adaptive Travel Assistance
Malamatinos, M.-C., Dimitriadis, I., & Vakali, A. I. (2026) · IEEE Mediterranean Electrotechnical Conference (MELECON) · doi:10.1109/melecon64486.2026.11418850
“RAG models integrate exter-nal knowledge retrieval before generation, helping to mitigate hallucination[5].”
Li, J., & Hu, X. (2026) · Across Languages and Cultures · doi:10.1556/084.2026.01190 · Cited by 1
Vu, T. T., Bui, T.-D., Nguyen, T.-T., Nguyen, S., & Vo, H. D. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.112852 · Cited by 7
Exploring General-purpose Autonomous Multimodal Agents for Pathology Report Generation
Aubreville, M., Donovan, T., & Bertram, C. (2026) · Informatik aktuell · doi:10.1007/978-3-658-51100-5_76 · Cited by 3
Robotic Sycophancy: A Scoping Review
Seaborn, K., & Yalçın, Ö. N. (2026) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3776734.3794532 · Cited by 2
Informed Skepticism: Navigating The Code Hallucination Dilemma
Faker, O., & Toker, Ş. (2026) · International Informatics and Software Engineering Conference (IISEC) · doi:10.1109/iisec69317.2026.11418436
“This problem happens because of the models’ statistical nature and training on bad data, or sometimes because they misunderstand a prompt [7][8].”
Hallucination-Free Causal Graph-Guided AI Framework for Intuitive Question and Answer Generation
Wang, N., & Katsaggelos, A. K. (2026) · International Journal of Multimedia Data Engineering and Management · doi:10.4018/ijmdem.404003 · Cited by 1
Du, W., Du, J., Zhang, H., et al. (2026) · Machines · doi:10.3390/machines14030322
LLMS, Manufacturing Knowledge Graphs & GraphRAG enabling Intuitive Analytics
Senington, R., Mittermeier, L., & Ng, A. H. C. (2026) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1342/1/012057
“Issues with LLMs are, however, also widely reported, where they fail to give correct results, such as is seen when they hallucinate [10, 11] and more specifically seen in a detailed analysis of their coding capabilities [12].”
Sardana, G. M., Sekti, B. A., Aryani, D. M., & Ariessanti, H. D. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/404019
No skin in the game: why agentic AI requires principal-agent governance
Prause, M. (2026) · AI and Ethics · doi:10.1007/s43681-026-01067-6 · Cited by 2
Wang, Q., Wei, S., & Yang, K. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423524 · Cited by 6
“First, due to their black-box nature, pure AI-based methods may not yield reliable decisions (e.g., hallucinations of LLMs [29]).”
Reflective LLM Prompt Optimisation for Interpreting GNN Predictions in Traffic Forecasting
Zhang, Z., Kim, J., He, D., & Yildirimoḡlu, M. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423238
“Concerns about LLM hallucination (plausible-but-incorrect outputs) are significant [28].”
Tang, K., Tong-Ho, H. N. H., Riegel, K., Denny, P. C., Giacaman, N., & Leinonen, J. (2026) · Australasian Computing Education Conference · doi:10.1145/3786228.3786249 · Cited by 2
Rahman, M., & Chowdhury, M. (2026) · International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE) · doi:10.1109/icecte69292.2026.11429437
“The study [23] suggested SAFE approach, an assessment technique for verifying long-form factuality in LLMs that greatly lessens hallucinations by using retrieval to base model development.”
LoCo-VLM: End-to-End Autonomous Driving with a Loosely Coupled Vision-Language Model
Xing, J., Min, S., Xie, D., Wang, X., Kang, L., Ren, Y. Q., Yu, H., & Bai, X. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423082
“However, most existing VLM methods heavily depend on the VLM’s output, which influences only a single trajectory, while the impact of large model hallucinations [26] is often overlooked.”
Volkle, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6300178
BetterCheck: Towards Safeguarding VLMs for Automotive Perception Systems
Dona, M. A. M., Cabrero‐Daniel, B., Yu, Y., & Berger, C. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423129 · Cited by 4
“However, due to the potential risk of hallucinations [9] generated by LLMs, the trustworthiness of such LLM-assisted systems and applications remains questionable.”
Ajraou, H., Ward, R., Farbiz, F., Graf, E. W., Yuan, M., Yan, S., & Oyekan, J. O. (2026) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2026.103277 · Cited by 1
Ratneswaran, S., & Ukkusuri, S. V. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423667
“However, these LLMs are black box models and suffers from hallucination [6].”
Martynyuk, P. (2026) · Modelirovanie, optimizaciâ i informacionnye tehnologii. · doi:10.26102/2310-6018/2026.54.3.008
Bauerdick, J., Streibel, L., Milde, M., et al. (2026) · Zeitschrift für wirtschaftlichen Fabrikbetrieb · doi:10.1515/zwf-2026-1010
Liu, J., Zhu, Y., Feng, J., Zhang, X., Zhou, Z., Tao, Y., & Duan, H. (2026) · PLoS ONE · doi:10.1371/journal.pone.0343823
“Despite BLIP2’s ability to generate captions for surgical images, it occasionally produces outputs that do not align with visual content, a phenomenon known as hallucination [24].”
Harnessing Large Language Models for Intelligent Transportation Systems: A Systematic Review
Kaur, S., Sehra, S. S., Ebrahimi, D., Wang, X., Singh, J., & Sehra, S. K. (2026) · Multimodal Transportation · doi:10.1016/j.multra.2026.100308 · Cited by 7
AIGC: From Statistical Methods to Cognitive Applications
Zhou, H., & Zeng, B. (2025) · International Conference on Computer Science and Information Technologies · doi:10.1145/3783862.3783894
Internet Appendix for "AI Adoption in Financial Markets and Information Quality"Preprint
Wang, K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6417059
An AI Education Framework Based on LLM-Knowledge Graph for Personalized Learning
Liang, Z., Wang, Y., Zhao, M., Feng, S., Zhang, Y., & Zhang, Y. (2025) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis69366.2025.11433876
“The educational application of LLMs is constrained by their tendency to generate plausible but factually incorrect content [8].”
ReFEND: Leveraging Social Sentiment Resonances for Fake News Detection
Guan, M., Shang, J., Xu, R., Hao, F., Li, R., & Min, G. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3676162
“Restrictions apply. concern is hallucination [52], [53], where the model generates content that sounds reasonable but lacks factual support.”
Mining Multimodal Fatigue Data Using Reasoning Foundation Models and Formalized Domain Knowledge
Mohanty, J. P., Thomas, A., Pollock, T. M., & Durmaz, A. R. (2026) · Integrating materials and manufacturing innovation · doi:10.1007/s40192-026-00442-9 · Cited by 1
“A key challenge that persists is hallucination, i.e., LLMs generating information not present in the source [44].”
BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets
Jonker, R. A. A., Martins, B. M. R. D. A., & Matos, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21321-1_62 · Cited by 1
“However, despite their success, LLMs struggle with factual consistency, often generating hallucinated or inaccurate responses [12,11].”
Speculative Retrieval-Augmented Generation for Faithful Question Answering in Aircraft Maintenance
Signé, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_50
Metacognitive Multi-agent Retrieval-Augmented Generation for Multi-hop Reasoning
Iturra-Bocaz, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_42
The 9th International Workshop on Narrative Extraction from Text: Text2Story 2026
Campos, R., Jorge, A. O. S., Jatowt, A., Bhatia, S., & Litvak, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_10 · Cited by 1
Towards terms definition extraction in drone forensics using large language model
Silalahi, S., Ahmad, T., & Studiawan, H. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200655
Plankl, M., Göbel, T., & Baier, H. (2026) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2026.302053 · Cited by 1
Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain
Asadi, M., Nedaee, T., O’Sullivan, J. W., Ashley, E. A., & Adeli, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38059-3_13 · Cited by 1
Akkaya, A. (2026) · Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi · doi:10.51513/jitsa.1848120 · Cited by 1
Research on a Mental Health Service System Based on an Improved RAG Algorithm
Chen, P., Liu, H., Zhang, Y., Yan, Y., Tang, Y., & Tan, D. (2025) · IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE) · doi:10.1109/iceace67491.2025.11439659
“Average Response Time: Measures the system's real-time performance, with the target being under 2 seconds to ensure a good user experience [39].”
Highly generalizable cross-domain machine-generated text detection
Xing, Y., Men, Y., Luo, S., Yang, Z., Zhou, J., & Pan, L. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133426
Sallai, T., Nitto, M. D., Catania, G., Zanini, M. P., Sasso, L., & Bagnasco, A. (2026) · Nurse Education in Practice · doi:10.1016/j.nepr.2026.104801
GD4LLM: How Layout Quality and Prompting Influence LLM Understanding of Graph Drawings
Didimo, W., Montecchiani, F., & Piselli, T. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3677884 · Cited by 3
“On the other hand, LLMs are prone to hallucination , that is, the generation of plausible yet nonfactual content [24].”
A Retrieval-Augmented Generation with Dual-Similarity Monitoring for Nuclear Energy Knowledge Q&A
Chiang, C.-H., & Lee, K.-C. (2026) · Applied Sciences · doi:10.3390/app16073182
Diren, D. D. (2026) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis...1869872
Age-inclusive shared mobility via agent-based modeling: Lessons from China for African cities
Clement, F. D., & Zhou, S. (2026) · Scientific African · doi:10.1016/j.sciaf.2026.e03320 · Cited by 1
Friedman, M., Sacks, K. N., Haziza, R., Zilberlicht, A., Chill, H. H., Rotem, R., Zvi, M. B., Grinstein, E., Spiegel, E., & Ginath, S. (2026) · European Journal of Obstetrics & Gynecology and Reproductive Biology · doi:10.1016/j.ejogrb.2026.115089
Lee, H. (2026) · Journal of Korean Academy of Nursing Administration · doi:10.11111/jkana.2025.0082
Diagnosing LLM Hallucinations in Process Mining Tasks: a Taxonomy and a Benchmark
Berti, A., & Kourani, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-17618-9_41
Bhargav, R., Dhamankar, S., Shashank, S., V, Parimi, M., & Wagh, S. R. (2026) · International Conference on Emerging Trends and Innovations in ICT (ICEI) · doi:10.1109/icei65890.2026.11447819
AssertGPT: LLM-driven assertion generation for programmable networks verification
Yao, Y., Tian, L., Hu, Y., Cui, P., Guo, X., & Li, K. (2026) · Computer Communications · doi:10.1016/j.comcom.2026.108508
Zhang, D., Tian, W., Tang, Z., Lu, Y., & Hu, W. (2025) · International Conference on Cyber Resilience and Endogenous Safety & Security (CRESS) · doi:10.1109/cress68073.2025.11452618
“…domain-aware priors—unattainable by traditional numerical models—enable LLMs to serve as a bridge between symbolic reasoning (e.g., attack stage logic) and statistical learning (e.g., feature correlation analysis), thereby simultaneously enhancing the interpretability and adaptability of IDS [11].”
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.