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 1,601–1,700 of 2,245
Khan, A., Khan, S., Khan, M. S. R., Su’ud, M. M., Alam, M. M., & Mallik, S. (2026) · Research Square · doi:10.21203/rs.3.rs-9707462/v1
Enhancing Digital Product Passports for the Circular Economy with Generative AI
Pourjafarian, M., Plociennik, C., Stein, P., Moarefvand, N., & Ruskowski, M. (2026) · Procedia CIRP · doi:10.1016/j.procir.2026.05.036 · Cited by 1
Hong, V. N., & Phuoc, H. T. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01455-1
“Modern large language models (LLMs) can make inferences from such texts, yet prompt-driven generation still lacks reliability in such applications: LLMs are likely to produce false relations, rephrase actions, or confuse the executor with related parties [1, 2].”
Technical Background: Large Language Models (LLM)
Lang, F. (2026) · Springer eBooks · doi:10.1007/978-3-662-73208-3_2
The Medium is the Prompt: Prompts as Design Science Artifacts
Schulte, K., Herath, S., Møller, F., & Legner, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-28316-0_18
Prompt Engineering: Good Question, Good Result
Lang, F. (2026) · Springer eBooks · doi:10.1007/978-3-662-73208-3_3
Rahman, M. N., Tahir, M., Isoaho, J., & Virtanen, S. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536475
“These behaviors present fundamental reliability issues for deploying LLMs in high-stakes forensic applications [18].”
Park, J., Le, J., & Cooper, H. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-27993-4_24
“Yet, they exhibit limitations such as hallucination, knowledge recency gaps and lack of domain specific or private knowledge [10,13,16].”
Hu, Q., Rong, X., Yesilbursa, M., et al. (2026) · Speech Communication · doi:10.1016/j.specom.2026.103428
Large Language Models for Web Accessibility: A Systematic Literature Review
Aljedaani, W., & Mollik, R. H. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800452 · Cited by 5
Kampourakis, K. E., Gkioulos, V., & Katsikas, S. K. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-27993-4_14 · Cited by 7
Cai, L., Meng, B., Huang, J., Ding, G., Ju, M., Wang, W.-W., Shi-jie, D., Lai, L., Wang, J., Yang, C.-X., et al. (2026) · LabMed discovery. · doi:10.1016/j.lmd.2026.100130 · Cited by 1
Parameter-Efficient LLMs for Flow-Based Intrusion Detection
Muhammad, M., Wunsch, A., & Sardy, L. A. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-27993-4_4
Sadallah, M., & Encelle, B. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800451 · Cited by 1
Kalyanaraman, S., Gupta, R., Joshi, A. S., Joshi, K. S., Suryawanshi, J., & Jadhav, V. (2026) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds69358.2026.11540259
AI-Assisted Diagnosis and Correction of Anomalies in Traditional Production Line
Chen, C., ZHANG, Z.-X., & Kang, J.-Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0074-0_19
On the creation of value achieved by harnessing large language models
Staegemann, D. G., Pohl, M., Haertel, C., & Turowski, K. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.04.042
Zheng, Z., Choi, Y., Huang, C., Cao, H., Tian, S., & Pei, T. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3699202
“These knowledge gaps lead to “hallucinations” in LLMs, hindering their real-world deployment and producing answers that are seemingly plausible but factually unsupported [7].”
Liu, H., Tao, L., Ji, H., et al. (2026) · Chinese Journal of Mechanical Engineering · doi:10.1016/j.cjme.2026.100331
Compliance-Aware Generative AI for Life Insurance Document Synthesis: A Reference Architecture
Siddhu, H. S., Pappu, K., & Thanvi, Y. S. (2026) · 2026 International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11541931
“Comprehensive surveys categorize hal-lucination types and mitigation strategies [6].”
Anomalies in AI Outputs Beyond Input Data Quality: The Significance of Reasoning
Royo, J. [. ]. A., Martín, Ó., Martínez, E., Montalvo, F. J. F., & Blanco‐Fernández, J. (2026) · Applied Sciences · doi:10.3390/app16115491
Chawla, R., Dahiya, S., Singh, G., & Fortino, G. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3691181 · Cited by 1
“However, one of the most critical challenges in this context of LLM is hallucination, where language models produce outputs that are not grounded in the source documents [19], [20], [21].”
Vanbrabant, S., Ruiz, G. A. R., & Vanacken, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-26051-2_10 · Cited by 1
A Comprehensive Analysis of Hallucinations in Large Language Models
Dakkak, N. A., Alkhazindar, M., & Bayrak, A. T. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537214
“Such outcomes reflect distortions in the underlying data rather than deliberate reasoning errors [1].”
InfluentialMou, Z., Tian, Z., Jin, J., Yu, H., & Huang, Y. (2026) · Biomolecules · doi:10.3390/biom16060830 · Cited by 1
“…the substantial advancements enabled by LLM-based methods, their application in drug repurposing is critically challenged by hallucination—the generation of outputs that are fluent and coherent yet factually incorrect, unsupported by available evidence, or inconsistent with input context [122,123].”
Graph-Enhanced LLM Architecture for Reliable Data Management: Design Principles and Proof of Concept
Azeroual, O., & Nacheva, R. V. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537059 · Cited by 1
Zhao, J., Shen, L., Shields, J., Huang, X., & Chokyi, S. (2026) · Journal of Social Work Practice · doi:10.1080/02650533.2026.2683352
Huang, Q., Zhu, Q. Q., Ding, Y., Wu, T., Wang, H., Wu, H., Sun, Q., & Wang, Y. (2026) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2026.107825
Self-citationГамалій, К., Пересунько, Є., Борисенко, А., & Каук, В. (2026) · ГРААЛЬ НАУКИ · doi:10.36074/grail-of-science.15.05.2026.111
Smart-PCLib: A LLM-based Multi-Agent Framework for Automated PCB Component Library Generation
Di, Z., Tu, J., He, Z., et al. (2026) · doi:10.23919/date69613.2026.11539310
“Furthermore, since these models are not inherently trained on the specific formats of specialized domains, they may produce inaccuracies or “hallucinations” when tasked with understanding and generating highly specific information [10].”
MeltRTL: Multi-Expert LLMs with Inference-time Intervention for RTL Code Generation
Mashnoor, N., Akyash, M., Kamali, H., & Azar, K. Z. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539088 · Cited by 4
“A growing literature studies internal representations to improve truthfulness and reduce hallucinations [32].”
Agentic AI Architecture for Multi-Criteria Decision-Making: A Collaborative Human-AI Framework
Ferreira, R., Araújo, M., Tereso, A., & Nováis, P. (2026) · Group Decision and Negotiation · doi:10.1007/s10726-026-10004-1 · Cited by 2
“…architecture, specialized AI agents are assigned to discrete stages of the decision-making pipeline, enhancing transparency and mitigating a critical limitation of conventional LLM-based systems, namely the propensity to generate inaccurate or logically inconsistent outputs (Huang et al. 2025).”
O 2 AS: Optimistic Online Aerial Search via Vision-Language Models
Allahham, M. S., Mohamed, A., Ismail, L. S., & Al-Obaidi, S. A. S. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3700561
“Their predictions may be noisy, biased, or systematically wrong in out-of-distribution environments, and they may hallucinate plausible but incorrect scene attributes [10].”
Towards higher quality and fewer hallucinations: A multi-agent collaboration framework for LLMs
Shen, S., Sun, D., Qin, Z.-X., Su, Y., Zhu, L.-B., Lu, J., Huang, Z.-Y., & Wang, S.-J. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104953 · Cited by 1
Owusu-Tweneboah, J., & Altarawneh, A. (2026) · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC) · doi:10.1109/satc69565.2026.11542569
“Recent advances in large language models (LLMs) support automated interpretation of regulatory text and compliance documentation [4]–[6], motivating the incorporation of verification and governance mechanisms for high-assurance use [7]–[9].”
Su, S., Huang, J., Wu, M., et al. (2026) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2026.102343
Polishing slurry chemical formulation design driven by large language models
Yang, Y., Huang, Q., Li, Y., Zhu, L., Wu, T., & Wang, Y. (2026) · doi:10.1145/3808871.3808880
Farsi Natural Language Processing: A Survey
Bokaei, Z., Magdy, W., & Webber, B. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104912
ETFAgents: A Multi-agent System with a Single LoRA-fine-tuned Agent
Pan, Y., Liu, X., & Chu, C. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01401-0
“However, recent studies show that multi-agent prompting can improve reasoning and factuality only as a soft constraint [31], and that LLMs remain prone to hallucinations that can propagate within agentic workflows [32, 33].”
Agentenbasierte Fahrgastinformationssysteme für den ÖPNV
Palk, M., & Voß, S. (2026) · HMD Praxis der Wirtschaftsinformatik · doi:10.1365/s40702-026-01283-y
LGMT: Logic-Grounded Metamorphic Testing for evaluating the reasoning reliability of LLMs
Zhou, Z., Li, M., Fang, X., Zhou, X., Lin, W., & Zheng, Z. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116324 · Cited by 5
“This property is critical for LLM-integrated software systems, because inconsistent reasoning under semantically equivalent inputs may lead to unreliable decisions even when the model appears accurate on individual benchmark instances [17, 45, 48, 42].”
Liang, W., Yang, J., Li, S., Luo, P., Deng, H., & Li, T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6902284
El Kayali, M. K., Neumann, E. M., Fahy, S., Bartek, B., Oehme, S., Getgood, A., Jung, T., & Milinkovic, D. D. (2026) · Journal of ISAKOS · doi:10.1016/j.jisako.2026.101160
Personalized smart courses for university physics based on knowledge graph and large language models
Yin, W., Yan, Z., Qi, Z., & Zhang, R. (2026) · Interactive Technology and Smart Education · doi:10.1108/itse-10-2025-0313 · Cited by 1
ReGeS: Reciprocal Retrieval–Generation Synergy for Conversational Recommender Systems
Yang, D., & Fang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7251-9_6 · Cited by 2
Evaluating Knowledge Preferences in Question Answering via Bloom’s Taxonomy
Bimberg, R., Huber, M., Kammer, F., Meintrup, J., & Siepermann, M. (2026) · ACM Symposium on Applied Computing · doi:10.1145/3748522.3779834
Transductive data augmentation framework for cross-domain ASTE using large language models
Ma, Z., Yang, L., Gu, M., & Wang, N. (2026) · International Journal of Web Information Systems · doi:10.1108/ijwis-12-2025-0446
Zhang, N., Mao, H., Zhang, S., Liu, X. M., & Jiang, H. (2026) · Neural Processing Letters · doi:10.1007/s11063-026-11857-y
“However, compressed models still suffer from static knowledge limitations and hallucination issues, where models generate plausible but factually inaccurate content [3].”
Rieger, N. (2026) · Bled eConference · doi:10.18690/um.fov.4.2026.1
Shen, S., Yi, L., Wang, J., Duan, J., & Chen, Y. (2026) · International Conference on Energy, Electrical and Power Engineering (CEEPE) · doi:10.1109/ceepe69795.2026.11552122
“Despite this advantage, a pure language model is not reliable enough for operational decision making [11].”
IFCoT: Insights Fusion Chain of Thought for Multimodal Reasoning in LLMs
Liu, J., Du, J., Hu, T., Tong, L., Feng, Y., Zhou, J. T., Xu, M., & Liu, Z. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3702539 · Cited by 1
“As such, their e ff ectiveness is bottlenecked by the precision of prompts within this single thought path, as well as the problem of hallucinations in LLMs [22], [23].”
Rodríguez-Rivera, P., León, A. M., & Rodríguez-Ferrer, J. M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7472-7.ch005
Shujaat, S., Pillai, A. G., Riaz, M., Alharbi, W., Ganganna, K., Alfadley, A. A., Aboalela, A. A., & Abolemaaty, W. (2026) · Head and Neck Pathology · doi:10.1007/s12105-026-01929-9
BanglaRAG: Building a Low-Cost Multilingual Knowledge Backbone for an Agentic LMS Assistant
Khandaker, S., Hasan, M. M., Roy, S. K., Pranto, F. S., Mamun, A. A., & Haque, A. (2026) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain69676.2026.11545902 · Cited by 1
“But ungrounded generation, for example, "hallucination" and unequal administration are a hindrance to reliable classroom application, and architectures that limit the results of models to institution-specific, vetted sources are encouraged [3].”
Alsayyed, R., Khelfa, S., & Hawash, A. (2026) · ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS) · doi:10.1109/icetsis68266.2026.11549183
Assessment of Ethical Design ChatBots by Factorized Conversational Interrogation
Khan, J. I., & Prithula, S. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-26349-0_45
Kumar, M., Patouillard, L., Donaldson, A., Cornago, S., Bartocci, P., Tu, Q., Wachter, H. D., Hübner, N., Dumont, M., Coroamă, V. C., et al. (2026) · The International Journal of Life Cycle Assessment · doi:10.21203/rs.3.rs-9984806/v1
MetaEmbody: Supporting Embodied Metaphor Ideation for Tangible Interaction Design
Guo, P., Zhang, J., Shi, H., Xu, H., & Dong, Z. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3812967
Che, H., Ye, F., Hu, X., & Zhou, Y. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3813015 · Cited by 1
Demystifying LLM API Misuses: A Lifecycle-Based Empirical Study on Real-World Android Apps
Wen, J., & Zhao, Q. (2026) · ACM Conference on Data and Application Security and Privacy (CODASPY) · doi:10.1145/3800506.3803496
Zhang, W., Huang, J., Bi, Z., & Wang, B. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116400 · Cited by 1
The Case for Repeatable, Open, and Expert-Grounded Hallucination Benchmarks in Large Language Models
Norman, J., Rivera, M. U., & Hughes, D. A. (2026) · International Conference on Information and Computer Technologies (ICICT) · doi:10.1145/3803291.3803328 · Cited by 1
Should we have a blind faith in the ChatGPT of generative AI in the tourism sector?
Kim, H., & Lee, S. (2026) · Journal of Travel & Tourism Marketing · doi:10.1080/10548408.2026.2667928 · Cited by 2
“Firstly, regarding inaccurate or biased information, ChatGPT generates text based on its training data, which may not reflect real-time updates and could rely on outdated or incorrect sources (Augenstein et al., 2024; Huang et al., 2025).”
Li, H., Liang, H., Wang, Y., Wen, H., & Liu, X. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133318
Yao, Z., Xu, Y., Xia, T., Chen, Z., Pan, E., & Xi, L. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02897-1
Yang, L., WANG, L. C., Ma, Y., Liu, J., & Zhao, S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116480
irAE.AI: AI-powered exploration of real-world immune-related adverse events
Fort, G., Dm, S., Lin, C.-N., Young, A., & Tan, A. C. (2026) · JAMIA Open · doi:10.1093/jamiaopen/ooag094 · Cited by 1
“Since hallucination is a well-recognized issue with LLMs, 40,41 we implemented multiple safeguards across our system to mitigate this risk.”
Sagastizabal-Sáez, A., Quintana, N. B., & Portillo, J. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2026.2685311
MCHRAG: Multi-Centroid Hierarchical Indexing for Efficient Incremental RAG
Ren, Y., Liao, M., Zhou, G., Peng, J., & Lv, P. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810580
A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding
Wang, S., Zhu, H., Huang, J.-H., Shen, Y., Zeng, C., Rudinac, S., Kackovic, M., Wijnberg, N. M., & Worring, M. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810730 · Cited by 3
Zhang, Z., Zhao, D. Y., He, T., Wang, Z. G., Li, X. Q., & Ma, H. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3810190 · Cited by 2
Wu, Z., Wang, Z., Xie, J., Li, J., & Fan, M. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3810207 · Cited by 1
Feakins, S., Habli, I., Littler, K., & Palin, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35506-5_8
Implementação de um Workflow Multiagentes para Recuperação de Informação Organizacional
Moretti, G. L., Sousa, K. D. S., Mendes, M. D. S., & de Oliveira, M. (2026) · Revista Eletrônica de Iniciação Científica em Computação · doi:10.5753/reic.2026.7184
Hu, S. (2026) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit70033.2026.11557775 · Cited by 5
“…adjustment, 20% of the test set), prompt injection samples (used to insert malicious misleading instructions, 20%, drug name obfuscation samples, similar drug name for 20%, and false evidence splicing samples (combining fake medical evidence, 20%), and the remaining 20% are normal samples [9].”
Liang, Z., Luo, B., Zhang, X., Zou, Y., & Ke, N. (2026) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit70033.2026.11557875
“For queries that demand multi-step reasoning, the reasoning chain is prone to fragmentation, which amplifies answer drift [4].”
MLLM-Based Textual Explanations for Face Comparison
Sony, R., Jain, A. K., & Ross, A. (2026) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf68042.2026.11558159 · Cited by 2
Romero, A. B. L., do Carmo, P. R. X., Filho, A. T. D. O., Kelner, J., & Sadok, D. F. H. (2026) · doi:10.5753/sbrc.2026.19300
“Despite this potential, the direct application of generic models in specific domains, such as the computer networking sector, faces critical challenges, such as the occurrence of hallucinations, sensitivity to noise, and limitations in causal inference from partial observations [Huang et al. 2025].”
A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning
Liu, J., Chen, Z., Qiao, S., Ju, M., Zhang, D., Han, B., Yu, S., Shu, X., Wu, J., Wen, D., et al. (2026) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew71238.2026.00024 · Cited by 9
“This limitation frequently leads to hallucinations—the generation of statements that are linguistically plausible yet unsupported by reliable evidence [10].”
Hierarchical Risk Control in Power Grid Emergency RAG via Domain-Specific Counterfactual Probing
Deng, C., Lei, K., Li, W., & Wang, Y. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11543003
“When retrieved knowledge is outdated, incomplete, or unreliable, the model may still generate highly confident outputs that fail to meet actual safety requirements or domain constraints [8], [33], [34].”
Second International Workshop on LLM+Vector Data: Agentic RAG Edition
Khan, A., Luo, Y., Özsu, M. T., Qi, D., & Wang, J. (2026) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew71238.2026.00017
Медианные значения метрик соответствия для классов SUPORT и CONTRADICT
Кузнецов, И. (2026) · Cifra LLC Journals · doi:10.60797/irj.2026.168.94.4
Кузнецов, И. (2026) · Международный научно-исследовательский журнал · doi:10.60797/irj.2026.168.94
An explainable question answering system for equipment maintenance with knowledge-enhanced LLM
Yang, Y., Mu, W., Chen, Y., & Fang, X. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02891-7
Jeong, Y., Cha, H., & Suh, E. E. (2026) · JMIR Cancer · doi:10.2196/96241 · Cited by 5
“Simultaneously, LLMs carry safety risks, including hallucinations and responses that may pose psychological risks to vulnerable patients [6,7,19].”
Teng, J., & Cho, S. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2026.2676667
Основные этапы комплексной оценки соответствия научных утверждений информации из первоисточника
Кузнецов, И. (2026) · Cifra LLC Journals · doi:10.60797/irj.2026.168.94.3
Современные методы повышения качества цитатно-осведомленной суммаризации
Кузнецов, И. (2026) · Cifra LLC Journals · doi:10.60797/irj.2026.168.94.2
InScribe: Intelligent Augmentation of Natural-Language Statements with Data Facts
Chen, C., Liu, Y., Shi, D., Cao, S., & Cao, N. (2026) · IEEE Pacific Visualization Conference (PacificVis) · doi:10.1109/pacificvis68791.2026.00021
“To address these issues, future research could explore task-specific fine-tuning [24] and reflection modules [30] to improve the agent’s accuracy and reliability.”
Основные этапы цитатно-осведомленной суммаризации
Кузнецов, И. (2026) · Cifra LLC Journals · doi:10.60797/irj.2026.168.94.1
Fusing LLMs and Genetic Algorithm for High-Quality Unit Test Generation
Fu, Y., Gao, X., Qi, B., Yuan, Y., & Sun, H. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3819237
AI Incident Auditor: A Retrieval-Augmented Framework for Post-Hoc Forensics of LLM Outputs
Chandel, Y. S., Varshney, S., Joshi, V., et al. (2026) · doi:10.1109/icici68867.2026.11565049
“…alignment between prior research and the main capabilities needed for the forensic analysis of LLM incidents, namely: incident detection, explanation of incidents, log retrieval via semantic similarity, chain-of-thought reasoning, confidence scoring, and forensic analysis of logs [1]-[6],[8]-[13].”
InfluentialBeyond the Data: Architectural Choices for Imbalanced Learning in Vulnerability Detection
Foulefack, R. Z. L., Djifack, U. D., & Marchetto, A. (2026) · SN Computer Science · doi:10.1007/s42979-026-05164-5
“However, LLMs still suf - fer from important limitations, such as hallucination and non-deterministic behaviour, which can affect their reli - ability in security-related tasks [ 44].”
Large language model based expert assistant for workflow consistent NPR-DDA analysis
Chen, G., Wang, X. H., & He, M. (2026) · Intelligent geoengineering. · doi:10.1016/j.ige.2026.06.010
Schaftner, S., & Gaedke, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29372-5_22
Harrag, F., Mecheddal, H., Ayat, N., Deriche, M., & Shaalan, K. F. (2026) · International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd69655.2026.11558974
“While approaches such as Reinforcement Learning from Human Feedback (RLHF) and post-hoc tools like the Perspective API have improved safety, they often remain rigid, computationally costly, or insufficiently sensitive to contextual and topical variations [1], [2], [5], [9].”
Alshehhi, A. M., & Zakaria, K. A. I. (2026) · International Conference on Integrated Intelligence and Cognitive Engineering (ICIICE) · doi:10.1109/iciice69672.2026.11565268
“Prior work often separates hallucinations into intrinsic hallucinations, which contradict the provided context, and extrinsic hallucinations, which introduce unsupported content beyond the source material [1], [2].”
Match me if you can: aligning historical posters and newspaper articles via multimodal deep learning
Xu, F., Düring, M., & Leiva, L. A. (2026) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqag088
Xu, S., & Zhao, J. (2026) · Systems and Control Transactions · doi:10.69997/sct.104078
Lanz, V., Datseris, A., Boytcheva, S., Mayer, J. H., Zikánová, Š., Mikulík, R., & Pecina, P. (2026) · Journal of Medical Internet Research · doi:10.2196/96347
“This limitation is particularly critical in the clinical domain, where we might need to extract life-critical information, and is further complicated by the phenomenon of hallucinations in generative models [50].”
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.