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 1,101–1,200 of 2,245
KI-Unterstützung zur Verarbeitung von Text- und Umweltdaten in der Gefährdungsbeurteilung
Westhoven, M., & Dietz, A. (2025) · Zeitschrift für Arbeitswissenschaft · doi:10.1007/s41449-025-00482-5
Skeptik: A Hybrid Framework for Combating Potential Misinformation in Journalism
Fan, A., Lei, F., Corman, S. R., & Maciejewski, R. (2026) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3766891 · Cited by 1
Legal Knowledge Generation Based on LLM Prompt Engineering
Yang, A., Zhao, L., & Gong, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06326-7_2 · Cited by 1
Statistical Learning Does Not Always Entail Knowledge
Pachón, D. A. D., Gallegos, H. R., Hössjer, O., & Rao, J. S. (2025) · Bayesian Analysis · doi:10.1214/25-ba1553 · Cited by 3
Responsible AI in Action: Navigating the Ethical Landscape of ChatGPT
Tiwari, A., & Kumar, P. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-0877-7.ch008
AI-Driven Multimodal TMJ Patient Modeling: From Unstructured Notes to Precision Treatment
Gaydamour, A., Tulissi, E., Mattos, C. T., Teixeira, R., Shin, M., Hershey, A., Kwon, A., Miranda, F., Gurgel, M., Barone, S., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05479-1_5
Architectures of Error: A Philosophical Inquiry into Human and AI Code
Sartori, C. C. (2026) · Philosophy & Technology · doi:10.1007/s13347-026-01056-x · Cited by 2
Chatbots integrated in the metaverse: a conceptual model based on interaction ritual chain theory
Yan, Y., & Fan, M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3235 · Cited by 1
Islam, M. A., Ellison, N., Lakha, B., & Serra, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06109-6_4 · Cited by 1
Liu, H., Dai, L., & Jiang, H. (2025) · Applied Sciences · doi:10.3390/app151910696
MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Model
Chen, Y., Habchi, S., & Wei, L.-L. (2025) · International Conference on Automated Software Engineering · doi:10.1109/ase63991.2025.00012 · Cited by 2
“To mitigate unrealistic expectations that may misalign with the game state [21], [22], we apply Prompt Chaining as introduced in IV-A2.”
Rapid Agrichemical Inventory via Video Documentation and Large Language Model Identification
Anastario, M. P., Armendáriz-Arnez, C., Largo, L. S., Gordon, T., & Roberts, E. (2025) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph22101527
Product Market Competition and Corporate Disruptive Innovation: A Large Language Model ApproachPreprint
Hu, N., Liu, Y., & Wang, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5542498
Chen, L., Jiang, P., Shen, Y., Yang, X., Pan, X., Chu, J., Liu, J., Sun, G., & Liang, R. (2025) · Visual Informatics · doi:10.1016/j.visinf.2025.100281
A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants
Bayazıt, B., Li, Y., & Si, X. (2025) · ACM SIGPLAN International Workshop on Language Models and Programming Languages (LMPL) · doi:10.1145/3759425.3763391 · Cited by 5
The LLM Era Demands Natural-Language-Aligned Theorem Provers for Mathematics
Cao, Q., Xie, L., & Yan, J. (2025) · ACM SIGPLAN International Workshop on Language Models and Programming Languages (LMPL) · doi:10.1145/3759425.3763384 · Cited by 2
Integrating LLMs with QC-OpenDRIVE: Ensuring Normative Correctness in Autonomous Driving Scenarios
Müller, J., de Graaff, T., & Möhlmann, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-07132-3_7 · Cited by 2
An LLM-Based Active Assistant and Smart Manual for CT Imaging Workflows
Mamaghani, Z. A., Vorberg, L., Maier, A., Katzmann, A., & Taubmann, O. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-07502-4_6
Navarro, T. (2025) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1109/icmlt65785.2025.11193354
“A significant issue associated with large language models is their tendency to generate outputs that lack a solid foundation in their training data or are entirely fabricated, a phenomenon widely recognized as hallucination [8, 9].”
BLADE: Brainstorming LLMs as algorithm designer through evolution for online subset selection
Qin, Z., Wang, C., Guo, J., Qin, H., Shen, P., & Weijia Jia, B. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115890 · Cited by 1
Fang, X., Yuan, H. R., Li, H., Kou, J., Gu, C., Zhang, W., Duan, X., & Fang, Y. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189217 · Cited by 4
“One major coverage gap of knowledge boundary formation is temporal staleness: the model’s knowledge is frozen at the time of pre-training without outdated information and fails to keep up with the rapidly evolving world [26], [39].”
InfluentialMethoden zur raschen Erkennung neuer Objekte in Farb- und Tiefenbildern
Vincze, M., Weibel, J.-B., Ausserlechner, P., Hönig, P., Sebeto, P., Pratheepkumar, A., Gupta, H., & Thalhammer, S. (2025) · e+i Elektrotechnik und Informationstechnik · doi:10.1007/s00502-025-01346-w
Designing Generative Multi-Agent Systems for Resilience
Dao, N.-L., & Moser, B. R. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.08.189
COLLAB-RAG: Cognitive Orchestration of Latent Logic via Multi-Role Adversarial RationalisationPreprint
Zhang, K., han, X., Liu, C., Tian, Y., yuan, D., & Cheng, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5617131
AI-Generated Feedback in Higher Education: The Tool for Analytic Rubrics
Rüdian, S., Kužílek, J., Ruhland, C., Elsir, Y., Kretschmer, M., Podelo, J., & Pinkwart, N. (2025) · IEEE International Conference on Advanced Learning Technologies (ICALT) · doi:10.1109/icalt64023.2025.00111 · Cited by 1
“When asking an LLM for numerical responses, they might not be accurate [15].”
Prompt Engineering: Gute Frage, gutes Ergebnis
Lang, F. U. (2025) · Springer eBooks · doi:10.1007/978-3-662-71542-0_3
Recognizing "Conformity Bias" in Large Language Models: A New Risk for Clinical UsePreprint
Nowroozzadeh, M. H., & Salari, R. (2025) · Research Square · doi:10.1101/2025.10.19.25338293
“[7] Similarly, reinforcement bias has been recognized, where models gradually adapt their outputs to user feedback over the course of prolonged interactions, reinforcing inaccuracies if they are repeatedly confirmed by users.”
SHAPE: Symptom-based Hallucination-driven Augmented Prompt Engineering (Preprint)Preprint
Kim, Y.-J., Shin, J., You, H.-S., Yoon, S., An, D.-J., Lee, A.-Y., Yoo, I.-S., Jeon, H. J., Lee, J. W., & Kim, K. D. (2025) · doi:10.2196/preprints.86028
F(r)iction in Machines: Accounting Hallucinations of Large Language ModelsPreprint
Wang, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5629978
Wie funktioniert ein Sprachmodell?
Lang, F. U. (2025) · Essentials · doi:10.1007/978-3-658-49885-6_2
How far are we from the era of big data in transcriptomics? Lessons from the bacterial data in GEO
Escobedo-Muñoz, A. S., Carmona-Campos, D., Trapaga, A. G. G., & Freyre-González, J. A. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf560
“An alternative is manual curation of the training data to remove bias and increase training data quality [67].”
Audio Prototypical Network for Controllable Music Recommendation
Öncel, F., Penaloza, E., Wu, H., Gupta, S., Ravanelli, M., Charlin, L., & Subakan, C. (2025) · Machine learning for signal processing ... · doi:10.1109/mlsp62443.2025.11204230
“Yet, as noted earlier, these explanations might not be actionable by users or contain truthful information [14].”
JailFact-Bench: A Comprehensive Analysis of Jailbreak Attacks vs. Hallucinations in LLMs
Nambiar, S., & Pöpper, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-01823-6_2
Perez, M. F., Yang, Y., Zha, Y., Ma, E., Tamboli, D. N. A., Ma, H., Shahriari, R., Pathak, V., Kasinets, D., Venkatakrishnan, R., et al. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754479
Multi-Layer Prompt Engineering for Intent Recognition in Travel Planning Assistants
Huang, Y., Ma, L., & Wang, Y. (2025) · Applied Sciences · doi:10.3390/app152111442 · Cited by 1
Discovery Omnia: Dynamic RAG for Enhanced Patent Analysis and Systematic Innovation
Avogadri, S., Alzetta, G., & Russo, D. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-08847-5_6 · Cited by 1
Orion: A Multi-Agent Framework for Optimizing RAG Systems through Specialized Agent Collaboration
fang, X., Xie, L., Yang, W. Z., Zhang, T., Zhang, R., Wang, H. H., Wu, D., & Pan, Y. (2025) · Asia-Pacific Symposium on Internetware · doi:10.1145/3755881.3755909 · Cited by 2
Self-citationGyadu-Asiedu, N. A. A., Aigbavboa, C. O., & David, M. M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-07992-3_16
Xu, Y., Xuan, Y., & Zheng, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5651130
Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
Li, B., Gao, D., Wang, Y., Jin, L., Yu, S., Cai, X., & Yang, L. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209139 · Cited by 2
“Hallucination in LVLMs stems from multiple complex factors [10], [39].”
RJAG: Retrieval Judgment Augmented Generation
Wang, K., Hu, Z., Ren, M., & Tao, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-2725-0_15
Srivastav, J., Banerjee, J., Singh, A., Jindal, S., & Mohapatra, A. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-03072-6_9
Trust-Aware Human–Robot Collaborative Decision-Making With LLM-Generated Data
Du, B., Li, P., Zhang, S., Liu, H., & Yu, Y. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3628551 · Cited by 1
“To address this issue, we adopt the method proposed in [21] by implementing a reflection agent powered by an LLM (ChatGLM-6b).”
Cao, L., Nguyen, T., Reisert, P., Nichols, E., Maeda, C., Lam, D., Siskind, S. R., & Gómez, R. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217859 · Cited by 1
“A significant limitation of LLMs is their tendency to produce hallucinations [22] and out-of-date information [23].”
PentestMCP: LLM and MCP Based Multi-Agent Framework for Automated Penetration TestingPreprint
Zhai, J., Zhou, X., Miao, H., et al. (2025) · Research Square · doi:10.21203/rs.3.rs-7582841/v1
Yu, T., Wang, H., Li, S., Luo, Y., Xian, L., He, H. X., Gong, H., Zhu, T., & Ye, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5704125
Self-citationBasu, R., Das, A., Gupta, P., Sen, S., Sadhukhan, B., & Das, N. (2025) · International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) · doi:10.1109/iacis65746.2025.11211373
“Despite their success, abstractive models face challenges such as hallucinations—generating inaccurate or irrelevant content—and require significant computational resources [11].”
Unstructured Medical Data Entry System using Gaussian Probabilities and Large Language Models
Koo, S., & Choi, K. (2025) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2025.23.10.23
SecuDevSLM: A Systematic Security Evaluation Framework for Small Language Models on Mobile DevicesPreprint
Li, Z., Tu, T., Lian, Y., Kong, Z., Liu, A. Q., & Li, W. (2025) · Research Square · doi:10.21203/rs.3.rs-7352742/v1
Switch, Reason, and Revise: Enhancing Reasoning Capability of Video Game AI by Large Language Models
Li, W., Liu, H., Lv, J., Huang, K., Song, A., & Lei, Z. (2025) · IEEE Transactions on Games · doi:10.1109/tg.2025.3630322
“They generate the plausible but factually incorrect contents when the reliable external sources like gaming rule databases are deficient [21].”
GenR1-Searcher: Curriculum Reinforcement Learning for Dynamic Retrieval and Document Generation
Wang, Y., Zhao, Y., Duan, R., Li, J., Wang, Y., & Zhang, K. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3760903 · Cited by 1
Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation
Kerdabadi, M. N., Moghaddam, A. H., Wang, D., & Yao, Z. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761388 · Cited by 9
C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation
Zhang, X., Liu, Z., Wang, J., Zhang, H., Xu, F., Zhang, J., & Wan, X. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761604 · Cited by 3
Dinh, D., Duong, H., & Nguyen, T. T. M. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-10209-6_13 · Cited by 1
Chen, Y., Zhang, R., Liu, Y., Zhu, T., Liu, M., & Lv, W. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4088-4_8
Liu, X., Yun, J., Li, B., Zhang, Y., & Shi, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4088-4_4
Park, S., & Jang, B. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3760823
A Multi-source Temporal Graph Approach for Reliable Market Forecasting with LLM Synergy
Shi, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3061-8_19
Vision, Voice, and Text: Pioneering Zero-shot Multimodal LLMs for Sentiment-driven Investment
Tan, S., So, C. C., Sun, Y., Wang, J., Loh, A. W.-K., & Yung, S. P. (2025) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3768292.3770368
Deng, Z., Zhang, M., Zhao, F., Wang, Y., Chen, B., & Xiang, N. (2025) · IntechOpen eBooks · doi:10.5772/intechopen.1012561
Knowledge Graph-Enhanced Large Language Model Approach for Device Fault Diagnosis Question Answering
Tu, Y., Sun, B., Wei, Z., & Song, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4472-1_26
TechSupportEval: An Automated Evaluation Framework for Technical Support Question Answering
Chen, B., Sun, Y., Liu, Y., Xu, L., Xie, Z., Pei, C., Han, J., Ni, F., Cai, X., Yang, C., et al. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227545 · Cited by 1
“This issue primarily arises from hallucinations in LLMs [12], [13] and the omission of relevant paragraphs when retrieving from knowledge bases [14].”
BlockQwen: A Robust LLM Powered by Blockchain and Smart Contracts
Kalari, S., Mukkamala, R., Ashok, V. G., Olariu, S., Bandara, E., & Shetty, S. S. (2025) · International Conference on Blockchain Computing and Applications (BCCA) · doi:10.1109/bcca66705.2025.11229516
“Additionally, retrieved context often lacks verifiable provenance, allowing outdated, corrupted, or adversarial documents to influence model reasoning [13].”
Enhancing Vector Data Quality through Negative Learning for Retrieval-augmented Large Models
Yao, L., Ma, K., Jin, R., Zheng, H., & Wang, D. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229352 · Cited by 2
“…retrieval context can lead the LLM to select words that do not fully align with the context when generating sentences, resulting in hallucinations [34], some studies [35] have found that the retriever’s highest-scoring documents are not directly relevant to the query (e.g., do not contain the…”
Distilling Calibration via Conformalized Credal Inference
Huang, J., Park, S., Paoletti, N., & Simeone, O. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227300 · Cited by 3
“AI Calibration aims to adjust AI models producing probabilistic outputs, avoiding overconfidence or underconfi-dence [1], [29]–[33] (e.g., mitigating LLM hallucinations [34], [35]).”
WHC-Eval:Evaluating Hallucinations in LLMs with Real-World Chat Data
Zhang, Y., Yun, J., Shi, X., & Liu, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229405
“Despite their widespread adoption in practical applications, LLMs remain susceptible to hallucinations - responses that appear plausible but are factually incorrect or do not accurately match user requirements[6].”
Robust Uncertainty Quantification for Factual Generation of Large Language Models
Zhang, Y., Yang, Z., & Zhou, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227634 · Cited by 2
“The hallucinations of LLMs can be categorized into factual hallucinations and faithfulness hallucinations [4].”
Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
Feng, Y., Zhao, S., Li, Y., Xiao, L., Wu, X., & Luu, A. T. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228609 · Cited by 4
“This lack of focus exacerbates the problem of hallucination—generating content that is either irrelevant or factually incorrect—particularly when dealing with long or complex texts [16].”
nie, Z., Li, J., & Zijun, N. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5758817
Enhancing Regulation-Adherent Requirement Engineering with Contextual AI: An Industrial Study
Sirin, O., Sami, M. A., Granlund, T., Rasku, J., Zhang, Z., & Abrahamsson, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-12092-2_5
Evidence Bound Clinical Decision Support with RAG
Şener, L. T., Yılmaz, U., Dikmen, I. C., Arı, A., & Karadağ, T. (2025) · Journal of Polytechnic · doi:10.2339/politeknik.1810629
Ddog: optimizing multi-hop inference via dual-driven retrieval and reasoning path
Chen, Y., Gu, B., Gao, L., Fu, K., Qu, Y., & Cui, L. (2025) · Machine Learning · doi:10.1007/s10994-025-06917-8
“For multi-hop inference tasks, where the question involves entities dispersed across multiple documents, incomplete retrieval or integration can cause the LLM to reason based on limited context, resulting in “logical hallucinations” (Huang et al., 2025).”
Zhang, Z., Pan, W., & Su, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5771190
Deepfake detection in the era of large models
Peng, C., Li, J., Liu, D., Wang, N., Hu, R., & Gao, X. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0289
Semantic Metadata Extraction from Online News Using a Modular Media Scraper
Marko, R., & Streicher, A. (2025) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct67853.2025.11239308
Wang, J., Duan, T., Yao, S., & Yasong, W. (2025) · International Conference on Artificial Intelligence and Digital Finance (AIDF) · doi:10.1145/3764727.3764767 · Cited by 1
LLMA4ITOps: A Lightweight LLM-Based Multi-Agent Framework for IT Operations and Maintenance
Jiang, Z., Zhang, T., Zhang, H., Xun, Y., Liu, Y., Feng, D., Si, W., & Zhang, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3346-6_36 · Cited by 1
Using a Large Language Model to Build a Vietnamese Natural Language Inference Dataset
Nguyen, C. T., Do, T. T.-T., & Nguyen, D. T. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4724-1_27
Prompt engineering experiment on ChatGPT’s ability to recommend orthopedic surgeons
Haupt, M. R., Massillon, D. R., Yang, L., Chen, Y., Natarajan, A., Ward, S. R., & Mackey, T. K. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2026.106581 · Cited by 1
LLM-Driven Information Integrity Preserving Segmentation for Cybersecurity Long DocumentsPreprint
Mei, G., Lin, J., Fu, W., Jian, L., Chen, C., & Wu, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5807310
Conversational A.I for Smart Exploration (C.A.S.E)Preprint
Abouelseoud, K., Soliman, F., Harb, M., Fekry, H., Mohamed, R., Barbary, N. E., Yousef, H., & Hindy, H. (2025) · Research Square · doi:10.21203/rs.3.rs-7802332/v1
An Interactive Video Learning Framework Enhanced by Large Language Models
Zhang, C., & Pang, G. (2025) · International Conference on Educational Technology and Artificial Intelligence (ICETAI) · doi:10.1145/3766557.3766635
“Moreover, the inherent hallucination phenomenon [11] in LLMs poses challenges to information reliability, which potentially generates inaccurate or fabricated content that may mislead learners.”
Instructing a Chatbot to Design Nucleic Acid Probes for Diagnostics
Chen, H., & Chan, W. C. W. (2025) · ACS Nano Medicine · doi:10.1021/acsnanomed.5c00062
CodeQUEST: Evaluation and Improvement of Code Quality Using LLMs
Lius, R., Frade, A., Vaidya, A., Labonne, M., Kaiser, M., Chakrabarti, B., Budd, J., Buford, J., Lin, X., & Moran, S. (2025) · IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW) · doi:10.1109/issrew67781.2025.00060
Hölzl, S., & Langenbach, C. (2025) · HMD Praxis der Wirtschaftsinformatik · doi:10.1365/s40702-025-01222-3
Multilingual Social Media Sentiment Analysis Via Fine-Tuned LLMS
Xie, J., Li, Y., & Jiang, Q. (2025) · International Conference on Culture-oriented Science & Technology (ICCST) · doi:10.1109/cost68045.2025.00023
“Moreover, natural language inference has been utilized to enhance sentence-level comprehension in cross-lingual contexts [11], drawing upon foundational theories of information communication [12].”
Provenance-Based CTI Analysis with Knowledge Graph and RAG (KGRAG)
Aki, I., Watarai, K., Okada, S., & Mitsunaga, T. (2025) · IEEE International Conference on Cyber Security and Cloud Computing (CSCloud) · doi:10.1109/cscloud66326.2025.00008
“Large Language Models (LLMs) are known to be prone to ”hallucination”—generating plausible but nonfactual content—a challenge widely documented in academic surveys [6].”
Evaluating Hallucinations in Large Language Models(LLM):Metrics and Mitigation
Koll, T., Babu, T., & Nair, R. R. (2025) · IEEE India Council International Subsections Conference (INDISCON) · doi:10.1109/indiscon66021.2025.11252341
“This literature review provides a clear overview of the state of the field currently through its breakdown of the findings and methodology of leading studies of the subject [5].”
R 3 AG 2025: Workshop on Refined and Reliable Retrieval-Augmented Generation
Yu, H.-T., Fang, Y., Ge, X., Xin, X., Wang, Z., Fu, J., Jose, J. M., Ma, W., & Ren, Z. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769524 · Cited by 1
Self-citationNarvekar, A., & Bajaj, R. (2025) · International Conference on Business Analytics for Technology and Security (ICBATS) · doi:10.1109/icbats66542.2025.11258092
“Several studies have look into the problem of hallucination which a major problem in applying LLMs for answers questions especially in legally binding domains [4,5].”
Yuan, Y., Ouyang, Y., Gao, W., Chen, L., & Zeng, Y. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109335
PlantPal: Tutoring Pest and Disease Knowledge via Large Language Models
Wei, Y., Guo, Y., & Wang, M. (2025) · doi:10.1145/3757372.3771857
“Empirical studies have reported that the hallucination problem has become a major technical challenge in domain-specific question-answering systems, with its incidence rate being non-negligible [Huang et al. 2025].”
van Miltenburg, E., & Lin, C. (2026) · Elsevier eBooks · doi:10.1016/b978-0-323-95504-1.01353-3
Harnessing large language models to build knowledge graphs from earthquake news
Bautista, L. R. P., Vilches‐Blázquez, L. M., & Jiménez, S. (2025) · International Journal of Digital Earth · doi:10.1080/17538947.2025.2594950 · Cited by 1
“…in the extraction of entities and relations (Lairgi et al. 2024), the generation of content that is seemingly plausible but not necessarily factual (Huang et al. 2024; Lairgi et al. 2024), and reliability and inconsistent responses or hallucinations (Huang et al. 2024; Wang et al. 2024) remain.”
Performance of reasoning large language models on nephrology multiple-choice questionsPreprint
Kitano, F., Masaki, M., Ichikawa, D., Shibagaki, Y., & Noda, R. (2025) · medRxiv · doi:10.64898/2025.12.03.25341427
Li, L., Deng, Z.-X., Chen, J.-C., Li, X.-J., & Wang, Q.-Y. (2025) · International Conference on Informatics and Analytics · doi:10.1109/icia64617.2025.11277854
“Early methods primarily focused on structured visual question answering (VQA), where models were trained on specific datasets to identify instruments, tissues, and actions in surgical videos [19], [20].”
SocraSynth: Adversarial Multi-LLM Reasoning
Chang, E. Y. (2025) · ACM eBooks · doi:10.1145/3749421.3749430
“Despite these promising developments, LLMs face challenges such as biases [Ferrara 2024, Parraga et al. 2023], hallucinations [Huang et al. 2025], and lim ited reasoning capabilities [Huang and Chang 2023].”
KAUFFMANN, T. M. A. L. (2025) · AI & Society · doi:10.1007/s00146-025-02786-w · Cited by 1
“This example illustrates what Huang et al. (2025) call a “factual hallucination” (making specific claims contra-dicting available evidence) and “reasoning hallucination” (logical inferences exceeding evidentiary support).”
Oladokun, B. D., Ogunjimi, B. E., Olatunbosun, I. E., Adefila, E. K., Abdul, A., Ebhonu, S. I., Omoniyi, Y. M., & Enakrire, R. T. (2025) · Journal of Library Metadata · doi:10.1080/19386389.2025.2598503 · Cited by 3
“This finding is consistent with Venkit et al. (2024) and Huang et al. (2023).”
Yuxia, S. (2025) · International Conference on Machine Learning, Pattern Recognition and Automation Engineering (MLPRAE) · doi:10.1109/mlprae67267.2025.11290735
“…[9], [10] and multimodal models [11]–[13], however, researchers have observed that, despite their rapid development, large models exhibit a tendency to hallucinate or provide inaccurate responses, leading to model outputs that appear reasonable but are, in fact, incorrect or incomplete [14], [15].”
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.