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 1,401–1,500 of 2,245
Ishadya, A. P. D., Withanaarachchi, A. S., & Jayalal, S. (2026) · International Conference on Advanced Research in Computing (ICARC) · doi:10.1109/icarc68737.2026.11453821 · Cited by 1
“Patient-facing chatbots that provide inaccurate or myth-reinforcing advice further risk confusion and loss of trust in healthcare providers [18].”
InfluentialDHR-LLM: A Dynamic Heterogeneous Redundancy Framework for Resilient Large Language Model Inference
Chen, P.-Y., Yu, Z., & Zhang, S. (2025) · 2025 International Conference on Cyber Resilience and Endogenous Safety & Security (CRESS) · doi:10.1109/cress68073.2025.11452519
“Safety concerns in LLMs stem from their probabilistic nature and imperfect data coverage, which make them prone to generating factually incorrect, logically inconsistent, or mis-leading outputs [22, 23].”
Cheng, H., Wang, K., Wang, Q., Liu, T., & Sheng, K. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114670 · Cited by 4
Self-citationDissanayake, S., & Wickramaarachchi, D. (2026) · International Conference on Advanced Research in Computing (ICARC) · doi:10.1109/icarc68737.2026.11454122
“Huang et al. [6] define three hallucination types: factual (contradicting verifiable facts), consistency (internal contradictions), and contextual (inappropriate for context).”
Peng, W., Chen, X., Fu, H., He, X., Wen, J., & Xue, Y. (2025) · International Conference on Cyber Resilience and Endogenous Safety & Security (CRESS) · doi:10.1109/cress68073.2025.11452349
“Due to its feasibility and efficiency, RAG is applied in various generation tasks with simple adaptation of the retrieval component, including open-domain question answering (OpenQA) [20], LLM hallucinations [21], [22], and some downstream applications [23].”
Self-citationAttribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey
Zhao, Y., Liu, Z., Zheng, Y., & Lam, K. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454197 · Cited by 5
GenAssist: Interactive Prompt-Driven XR Program Generation
Srinidhi, S., Singh, A., Lu, E., & Rowe, A. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr67842.2026.00081 · Cited by 2
“Although LLMs are powerful, it is well known that they can hallucinate and produce incorrect responses, especially when they lack up-to-date or domain-specific knowledge [17].”
Jeong, Y., Cha, H., & Suh, E. (2026) · doi:10.2196/preprints.96241
Logical reasoning in evolving scenarios: Evaluating LLMs with dynamic epistemic logic puzzles
Li, Z., Luo, J., & Liao, B. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115885
Cheng, X., Ran, Y., & Gu, Y. (2026) · Group Decision and Negotiation · doi:10.1007/s10726-026-09981-0 · Cited by 1
“Faithfulness errors occur when generated content deviates from user input or exhibits internal inconsistencies (Huang et al. 2025).”
SHOULD DATA ANALYTICS AND ARTIFICIAL INTELLIGENCE BE AN INTEGRAL PART OF CYBERSECURITY ASSURANCE?Preprint
Cheong, A., Kassar, M., He, L., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6514823
Guiding LLM-Based Loop Invariant Synthesis via Feedback on Local Reasoning Errors
Li, T., Yan, Z., Liu, J., Di, P., & Zhang, X. (2026) · ACM Transactions on Programming Languages and Systems · doi:10.1145/3806652 · Cited by 6
Governing Artificial Intelligence in the Evolving Academic Publishing Ecosystem
Karaarslan, E., & Aydın, Ö. (2026) · Journal of Metaverse · doi:10.57019/jmv.1899774 · Cited by 1
NeuroPath: Stepwise Knowledge Graph Reasoning with Neural Intelligence
Thai, P. K., Le, T. D., Bui, T., Quan, T., & Bui, T. V. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21625-0_3
Sequential Context Injection-Based Chunking for Mitigating Context Fragmentation
Lee, E.-J., Han, D.-S., Lee, S.-M., & Park, K.-S. (2026) · Journal of Digital Contents Society · doi:10.9728/dcs.2026.27.3.849
Parker, M. J., & Zavala-Cerna, M. G. (2026) · Education and Information Technologies · doi:10.1007/s10639-026-13902-8
“…content like transcripts to the prompt) can significantly mitigate the risk of LLM "hallucinations" (generating factually incorrect or non-sensical information) by providing the model with specific reference material, ex - amples of the desired task, and output format (Huang et al., 2025).”
Medical Question Answering System Based on Retrieval-augmented Generation
Cao, C. (2026) · ITM Web of Conferences · doi:10.1051/itmconf/20268401001
“Only a portion of their outputs can be trusted for accuracy and reliability; they lack domain-specific expertise, their knowledge may become outdated, and it is often difficult to trace their answers back to authoritative sources [1].”
Jansen, A., Sankaran, S., & Krahmer, E. (2026) · ACM Transactions on Computing for Healthcare · doi:10.1145/3806649
Li, Y., Wang, Y., Li, M., Li, X., & Feng, J. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115962 · Cited by 1
MG$$^2$$-RAG: Multi-granularity Graph for Multimodal Retrieval-Augmented Generation
Dai, S., Huang, Q., You, X., & Yu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_32 · Cited by 5
Generative models for clinical entity linking in Spanish
Zotova, E., Cuadros, M., & Rigau, G. (2026) · Array · doi:10.1016/j.array.2026.100805
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
Zhong, H., Sun, Y., Zhang, A., Wang, C., Chen, L., & Yang, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792720
Bowling with ChatGPT: On the Evolving User Interactions with Conversational AI Systems
Karnam, S. K., Dash, A., Gummadi, K. P., Mukherjee, A., Weber, I., & Zannettou, S. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792978 · Cited by 10
Beyond Factual Queries: A Novel Predictive Retrieval-Augmented Generation
Cheng, D., Deng, J., Chen, Q., Jie, J., & Gan, J. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792364
Self-citationPrivSniffer: Graph-based Contextual Privacy Leakage Detection for User-Generated Texts
Ye, H., Xiang, L., Huang, N., Yu, D., Zhang, L., & Wang, G. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792549
A Fact-Checking Framework with Denoising Evidence Retrieval and LLM-Based Debate Verification
Yang, J., Bai, Y., Song, D., Wu, Z., & Tian, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792285 · Cited by 1
Liu, Z., Wen, Z., Tian, Z., Huang, Z., Zhu, M., Wei, Z., Gao, Y., Ding, L., & Li, D. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792085 · Cited by 4
Mejía-Rendón, S., & Olezza, M. (2026) · trilogía Ciencia Tecnología Sociedad · doi:10.22430/21457778.3702
Retrieval Augmentation Reduces Factual Errors in Knowledge-Intensive Language Model Tasks
Dai, T., Zhang, C., & Zou, J. (2026) · Jisuanji shenghuojia. · doi:10.54097/8jvwpk07
“…of such parametric models is their tendency to generate factually incorrect statements with apparent confidence—a phenomenon broadly termed hallucination—arising because factual knowledge is stored implicitly within billions of fixed parameters that cannot be updated as the world evolves [2].”
Human-Machine Conflict in Human-Machine TeamingPreprint
Chen, M., Xiong, W., Tsao, L., & Ma, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6508019 · Cited by 1
Lanz, V., Datseris, A., Boytcheva, S., Mayer, J. H., Zikánová, Š., Mikulík, R., & Pecina, P. (2026) · doi:10.2196/preprints.96347
Nyay Mitra: An AI Powered Legal Assistance Platform Using Advanced RAG and FAISS Architecture
Patel, F., Patil, T., Pandey, U., & Bhangale, P. (2026) · International Conference on Communication, Computing and Emerging Technologies (IC3ET) · doi:10.1109/ic3et64989.2026.11467539
“In recent years many large language models like ChatGPT frequently give out false or information that is imaginary and doesn’t exist [5].”
Contributions to evaluating and improving the faithfulness for text generation
Zhang, K. (2025) · theses.fr (ABES) · doi:10.70675/28453a20z78f2z4fa2za6edz700065e69e97
Real-time Evaluation of RAG-based QA System Outputs
Jha, A. (2025) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet63943.2025.11471902
Erümit, S. F. (2026) · European Journal of Education · doi:10.1111/ejed.70616
Who Wants to be Rented? Rental Work and Digital Labour in the Age of AIPreprint
Tak, M. A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6560621 · Cited by 1
Inside the Newsroom: How Media Company AI Strategies Fall Short in Practice
Pedersen, T. M., Øvlisen, K., & Petersen, M. G. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3799296 · Cited by 1
Visualizing 30 Years of CHI Research with Generative AI
Oh, S.-Y., Katz, A., & McCrickard, D. S. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798338
Glanceable Verification Indicators for AI-Assisted Storytelling
Xu, M., Zhao, Z., Zeng, J., Wang, T. Y., Panetta, F., Fiebrink, R. A., Bryan–Kinns, N., & Grierson, M. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798491
Zhao, Z. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798387
Think Twice: Improving Privacy Awareness with Tailored LLM-Powered Interventions
Pias, S. B. H., Page, C. N., Chen, C., Amon, M. J., & Kapadia, A. C. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791583
Soft-Community Kernel Rényi Spectrum for Semantic Uncertainty Estimation in Large Language Models
Li, Z., & Du, J. (2026) · Entropy · doi:10.3390/e28040442
ArcMAP – ML assisted medical concept mapping to accelerate NHS data standardization
Cronin, J., Wiper, O., Poncet, A., Tait, K., Cooke, B., Fry, A., Baxter, J., & Dürichen, R. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1770903 · Cited by 1
Optimizing Long-Form Text Generation Using LLaMA Model
Mugali, A., Mugali, B., Desai, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-19179-3_1
Álvarez-Monsiváis, E., & Maltos-Tamez, A. L. (2026) · Feminist Media Studies · doi:10.1080/14680777.2026.2659313
Baid, A., Xue, Z., & Grauman, K. L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37038-9_4 · Cited by 7
AI Needs Your Body- Embodiment, Hapticity & New Ontic Spaces in the Age of AIPreprint
Tak, M. A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6585572
Multi-Layer LLMs for Secure Business Intelligence: A Case Study in Electricity Trading Analysis
Ren, Z., Jones, G., & Chen, L. (2026) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa67686.2026.11467825
“However, the output stability of LLM-based systems is often limited by the problem of hallucination [8].”
Padidela, S., Kalari, S., Ashok, V., et al. (2026) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa67686.2026.11468212
“Furthermore, these models are susceptible to generating incorrect or clinically inappropriate information, a phenomenon known as ”hallucination” [10].”
Malik, F. S., & Terzidis, O. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6599207
A perspective on hybrid intelligent computing for geospatial science
Li, Z., Chen, J., Ai, T., Yan, L., Liu, W., Zhu, Q., Gao, J., Shen, L., Lan, T., & Xu, Z. (2026) · Fundamental Research · doi:10.1016/j.fmre.2026.04.018
Assessing Llm Hallucinations And The Reliability Of Using LLms For Automated Hallucination DetectionPreprint
Cheong, J., Chen, D. S., Leung, W., Chou, C., Corcoran, C. M., Kelly, S., Bearden, C. E., Cecchi, G., Baker, J. T., Kane, J. M., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-9394250/v1
HyKAG: Hybrid Knowledge-Aware Retrieval-Augmented Generation for Knowledge-Intensive Questions
Zhao, Q., Wang, R., Zha, D., & Tang, Z. G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7078-2_33
Liu, S., Hu, M., Xu, X., Luo, W., Geng, G., & Luo, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7078-2_36
Llm-Based Framework for Improving Code Quality in Oilfield Data Acquisition Systems
Yang, W., Chen, J., & Estevez, C. (2026) · IEEE SoutheastCon · doi:10.1109/southeastcon63549.2026.11476591
“This issue stems from heavy reliance on pre-trained data and the probabilistic nature of language models, which often favor patterns from training data over true task comprehension [8].”
Lei, Z., Xu, Y., & Chen, S. (2026) · Applied Sciences · doi:10.3390/app16083963
Cheng, Y., Yin, J., Zhu, G., et al. (2026) · doi:10.1109/iscait69154.2026.11477374
“Compounding this challenge is, the inherent “hallucination” of the LLMs, which can result in suggestions lacking factual or regulatory grounding [6], [7].”
Liu, L., Yuan, Y., Liu, W., & Deng, F. (2026) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait69154.2026.11477359
“While LLMs exhibit strong capabilities in linguistic tasks, they struggle with complex numerical reasoning and multi-step logic, often exhibit numerical hallucinations [12].”
Zhu, Z., Yan, J., Zheng, W., Gong, W., Cao, J., Li, F., & Yan, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132537 · Cited by 1
Zhang, X., Zhang, S., Xiang, W., Xie, H., Tao, J., Wen, Z., Lv, Z., & Fan, C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464490
CITRAG : Contradiction Identification and Tracing for Retrieval-Augmented Generation
Huang, S., Lu, J., Xu, Y., Zhang, H., Xu, H., Tang, M., Wang, Y., & Gou, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462915
AFER: Adaptive Fact Selection via Entropy Reduction for Factual Long-Form Generation
Zhang, Y., He, R., & Wang, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460476
Logic-Oriented Retriever Enhancement via Contrastive Learning
Zhang, W., Jiang, Y.-H., Qi, C., Jia, R., & Wu, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465138
ReTools: Reflection-Enhanced Tool Invocation for Domain-Specific QA
Dong, F., Zhou, T., Zhang, M., Pan, X., Zhao, D., Xu, L., Wen, Y., & Yuan, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463575
OCWhy: Retrieval-Augmented Question Answering over Open CourseWare Lectures
Tecliceanu, M.-A., & Dascălu, M. (2025) · International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) · doi:10.1109/synasc69064.2025.00043
“Additionally, LLMs are prone to hallucinations, confidently generating plausible-sounding but objectively incorrect information, particularly when asked about topics beyond their training datasets or requiring specialized domain knowledge [5].”
DHEval: A Dynamic Hallucination Evaluation Protocol Robust to Data Contamination
Yin, J., Li, D., Wang, W., Yang, P., Wang, H., Ma, Y., Huang, Y., & Qi, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462032
Self-citationClueUp: Resolving Intent Ambiguity in Personalized Web Agents with Profile-Driven Clarification
Hu, D., Ge, J., Tang, W., Kong, H., Li, H., Wu, B., & Li, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464552
Borovina, R., & Mišić, M. (2026) · International Symposium INFOTEH-JAHORINA (INFOTEH) · doi:10.1109/infoteh68759.2026.11477693 · Cited by 1
“LLMs exhibit three critical limitations: hallucinations arising from reliance on statistical patterns rather than verified sources [1], outdated parametric knowledge that cannot be updated without costly retraining [2], and insufficient domain-specific understanding in specialized fields [3].”
Li, Z., Li, X., Mao, Y., Cao, L., Huang, W., Ren, J., & Yang, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461824
Zhang, B., Gao, C., Han, B., Hu, M., Luo, Z., Zhang, J., Yao, W., Bai, X., Geng, G., & Wang, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460764 · Cited by 1
DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
Wang, Y.-L., Fan, Y.-C., Li, J.-Y., Zhu, Z.-M., Mu, Y.-Y., He, Q.-Z., Xiao, T., & Zhu, J.-B. (2026) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp55912.2026.11462873 · Cited by 2
Do Multi-Modal LLMS Possess Compositional Zero-Shot Recognition Capabilities?
Xu, Y., Gao, S., Yang, G., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464961
LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?
Exler, D., Raimann, M., Münker, M. F., Rosin, M., Gómez, J. E. U., Niemeyer, C. M., Reischl, M., & Rettenberger, L. (2026) · Advanced Intelligent Discovery · doi:10.1002/aidi.202500197 · Cited by 1
Leveraging a Small Gemma Model to Predict Movie Ratings from Movielens Dataset: Preliminary Results
Neremzoiu, I.-D., & Bădică, C. (2025) · International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) · doi:10.1109/synasc69064.2025.00057
AI-Augmented Scenario Design: Experiences from a National Cybersecurity Exercise
Reuter, L., Smith, P., & Skopik, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-19540-1_16
Roostaee, M. (2026) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-026-01073-8
Enhancing Factual Reliability in Large Language Models Through Retrieval Augmented Generation
Shreya, S., Harsha, K. R. S., Nagaraj, S., & Rejental, S. (2026) · International Conference on Expert Clouds and Applications (ICOECA) · doi:10.1109/icoeca68095.2026.11485611 · Cited by 2
Zhang, S., & Wang, J. (2026) · Journal of China Computer-Assisted Language Learning · doi:10.1515/jccall-2025-0030 · Cited by 1
“More critically, beyond these stylistic and rhetorical fl aws, GenAI is also prone to “ hallucinations ” , generating plausible but factually incorrect or nonsensical content (Huang et al. 2025).”
Agada, J. O., & Biswas, A. (2026) · MRS Bulletin · doi:10.1557/s43577-026-01057-3 · Cited by 4
KEA Explain: A Neurosymbolic Framework for Explaining LLM Hallucinations
Haskins, R., & Adams, B. (2026) · Neurosymbolic Artificial Intelligence · doi:10.1177/29498732261443099 · Cited by 5
Nexarag: Democratizing Reproducible Knowledge Graph Contexts for LLM Research
Kerby, T., Fuller, B., & Moon, K. R. (2026) · The Journal of Open Source Software · doi:10.21105/joss.09910
Framing of higher education opportunities by large language models
Nikula, P. (2026) · AI & Society · doi:10.1007/s00146-026-03020-x
“…upon leading Western-developed LLMs, which may produce responses that diverge from those generated by non-Western models due to variations in training data and filtering processes (P. Huang et al. 2025; Cao et al. 2023), including factors such as state-imposed censorship (P. Huang et al. 2025).”
An AI-Assisted Computational Analysis of Landlord Concerns in Online Housing CommunitiesPreprint
Ren, C., Voodem, S. R., & Li, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6656018
Heo, S. (2026) · Scientific Reports · doi:10.1038/s41598-026-50127-8
Livia, D. P. R., Mincami, L. D. M., Ricapa, L. F. V., & Dávila, L. V. (2026) · Revista Venezolana de Gerencia · doi:10.52080/rvgluz.31.e15.4 · Cited by 2
Rethinking UX in the age of AI: DARPA’s Heilmeier Catechism at the interface 1
Prietula, M. J., O’Leary, D. E., & Swartout, W. (2026) · Journal of Decision System · doi:10.1080/12460125.2026.2655311 · Cited by 2
The Next Stage of Evolutionary Computation in the Era of Agentic Generative AI
Palk, M., Voß, S., & Glover, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-23607-4_19 · Cited by 1
An LLM-Based Multi-Path Question Answering System with XGBoost Routing and Threshold-Based Refusal
Dai, B., Li, C., Cao, Y., Ling, J., & Liu, X. (2026) · Electronics · doi:10.3390/electronics15091845 · Cited by 1
A neuro-symbolic approach for automatic assessment in ordinary differential equations
García, P., & Estrada, L. (2026) · Artificial Intelligence Advances in Education · doi:10.66818/aiaie.v1i1.917
Automated Localization of Affected Libraries and Versions from Vulnerability Reports
Xu, J. Q., Zhang, H., Zhou, X., Yang, Y., Hu, J., Li, X., Yang, L., & Liu, B. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3688559
“This indicates that LLMs suffer from hallucinations in their output, which undermines their reliability [77].”
Liao, X.-C., Mei, Y., & Zhang, M. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3689536
“Third, the factual accuracy and consistency of LLM reasoning can vary, potentially leading to unreliable or inconsistent control decisions in dynamic traffic scenarios [66].”
Zero-Shot Composed Image Retrieval via Dual-Stream Instruction-Aware Distillation
Zhong, W., Barton, R., An, W., Jiang, F., Ma, H., Guo, Y., Dan, A., Sam, S., Bouyarmane, K., & Huang, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02063 · Cited by 6
Self-citationLaMAR: A scalable architecture-Reward co-Design for expert systems in multi-Task robotics
Chen, K., Long, Y., & Shang, M. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132674
Gao, Z., & Liu, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116003
A Retrieval Augmented Generation Approach for Planning on General Purpose Service Robots
Attenborough, E., Arunachalam, H., Vásconez, J. P., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-16758-3_19
Large Language Models and Gender Bias: An Empirical AnalysisPreprint
ÇAKIR, P., & TEMİR, E. (2026) · Research Square · doi:10.21203/rs.3.rs-9577604/v1
A review of the applications and tasks of large language models in the legal field
Peng, G., Li, D., Wang, G., Guo, S., Su, L., & Yu, T. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3836 · Cited by 1
Masoumi, N., Davar, O., & Eftekhari, M. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02778-2 · Cited by 1
CLIP-IT: CLIP-based Pairing of Histology Images with Privileged Textual Information
Karimian, B., Avanzato, G., Belharbi, S., Guichemerre, A., McCaffrey, L. M., Shateri, M., & Granger, E. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00361 · Cited by 2
“Experiments 1 show that CLIP-IT consistently improves classification accuracy over both uni-modal and multimodal CLIP-based baselines in most cases, without requiring paired annotations per dataset or incurring additional inference-time complexity.”
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.