Survey of Hallucination in Natural Language Generation
Open accessThe DOI matches its Crossref record; 355 of the 360 references it cites were found in a registry or an index, and 4 are not checked yet; 224 of the 256 sources its claims cite were checked for support.
Abstract
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.
Verified 2026-11-19 · 4 references not checked yet
Overview
CoChat Summary
TL;DR
This survey provides a broad overview of hallucination in natural language generation, covering definitions, contributors, metrics, mitigation methods, and task-specific progress across summarization, dialogue, GQA, data-to-text, machine translation, vision-language generation, and LLMs. It distinguishes intrinsic from extrinsic hallucination and argues that hallucination must be treated differently across tasks and sources.
Key findings
- The survey categorizes hallucination into intrinsic hallucination, where generated output contradicts the source, and extrinsic hallucination, where output cannot be verified from the source; extrinsic hallucination is not always erroneous because it may come from factually correct external information.
- It reports prevalence examples from cited work: 25% of summaries generated by state-of-the-art abstractive summarization systems have hallucinated content; 62% of first sentences in WIKIBIO have additional information not stated in the corresponding infobox; and 74% of samples in the QMSum dataset consist of inconsistent facts.
- It reviews hallucination metrics as statistical, model-based (IE-based, QA-based, NLI-based, faithfulness classification, LM-based), and human evaluation, and mitigation methods as data-related and modeling/inference methods including architecture changes, planning/sketching, RL, multi-task learning, controllable generation, and post-processing.
- For LLMs, it notes that RLHF reduced the hallucination rate from 41% to 21% in closed-domain tasks for InstructGPT, and discusses reference-dependent and reference-free hallucination metrics plus mitigation via data refinement, RAG, safety fine-tuning, model editing, decoding methods, chain-of-thought variants, post-processing, and ensembling.
Methods
- Literature survey design: the paper reviews existing research on hallucination in NLG rather than conducting new experiments or primary data collection.
- Coverage: general NLG hallucination topics (definitions, contributors, metrics, mitigation, future directions) plus task-specific sections on abstractive summarization, dialogue generation, generative question answering, data-to-text generation, neural machine translation, vision-language generation, and large language models.
- Analysis: synthesizes and compares definitions, metrics, mitigation approaches, and future directions across tasks, with examples in tables and figures; the LLM section was updated in Jan 2024.
Limitations
- The paper states that GQA has no standard definition or categorization of hallucination and no automatic metric specifically for hallucination in GQA; it also notes that open-domain dialogue lacks a standard hallucination metric and that VL hallucination research is still in its early stage.
- The paper states that extrinsic hallucination has been somewhat overlooked and is more challenging to reduce, and that most existing mitigation methods do not distinguish between intrinsic and extrinsic hallucination.
- Evident from the text: as a survey, it does not provide new empirical validation of metrics or mitigation methods, and its LLM coverage is explicitly updated only through Jan 2024, so later work is not included.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
124 Valid · 26 Not valid · 19 Not checked · 135 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Furthermore, perturbation, where the insertions of most common tokens are placed at the beginning of the sentence, seems to be the most successful in hallucination mitigation.”
What the sources say
- Not checked — no full text of the sourcecites [133] [133] Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, and David Sussillo. 2019. Hallucinations in Neural Machine Translation. ICLR (2019). -
- Disputedcites [215] [215] Vikas Raunak, Arul Menezes, and Marcin Junczys-Dowmunt. 2021. The Curious Case of Hallucinations in Neural Machine Translation. (4 2021), 1172-1183. https://arxiv.org/abs/2104.06683v1 - sourceExperimental — accuracy not yet measured
In the passage describing the perturbation procedure (page unavailable), the paper says that inserting common tokens at the beginning is used to generate hallucinations, not mitigate them. Its prevention section instead discusses approaches such as robust learning and corpus-level filtering. (LLM, conf=0.92)
Checked by a reasoning model — may be wrong.
hedgedstates 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.
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“While there are works on the visual extension of faithfulness-oriented RLHF [303], these essentially involve labeling more data, which is expensive and difficult to scale.”
What the sources say
- Disputedcites [303] [303] Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and Tat-Seng Chua. 2023. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback. CoRR abs/2312.00849 (2023). https://doi.org/10.48550/ARXIV.2312.00849 arXiv:2312.00849 - sourceExperimental — accuracy not yet measured
RLHF-V does use human annotation for visual-model alignment, but it makes the contrary point about needing more labeled data. The Fine-grained Correctional Human Preference Collection section says its corrections improve data efficiency, and Section 4.3 reports comparable hallucination rates using only 200 preference examples versus an order of magnitude more ranking-labeled examples. Our copy does not establish a separate claim about annotation cost or scalability. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
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.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“Nevertheless, as illustrated by Falke et al. [66], off-the-shelf NLI models tend to transfer poorly to the abstractive summarization task.”
What the sources say
- Supportedcites [66] [66] Tobias Falke, Leonardo FR Ribeiro, Prasetya Ajie Utama, Ido Dagan, and Iryna Gurevych. 2019. Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . 2214-2220. - source
The Introduction states that models trained on NLI datasets transfer poorly to the paper’s downstream task of ranking generated summaries by correctness. The Conclusions likewise say that out-of-the-box NLI models do not perform well on that task. (LLM, conf=0.94)
- 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 wrong association results in generation with facts mixed up between two similar entities [60, 233].”
What the sources say
- Partly supportedcites [60] [60] Nouha Dziri, Andrea Madotto, Osmar Zaiane, and Avishek Joey Bose. 2021. Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding. EMNLP (2021). - sourceExperimental — accuracy not yet measured
The GPT2-KG passage describes an incorrect association between entities, and G Error Analysis gives an example of a generated response assigning a book to the wrong author. These support the claim that facts can be mixed up, but the paper does not say the entities involved are similar. The supplied passages do not provide page numbers. (LLM, conf=0.83)
- Supportedcites [233] [233] Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. EMNLP (2021). - source
The Introduction states that language models often mix up facts between two similar entities when generating factually incorrect statements. This directly supports the cited description of the resulting error. (LLM, conf=0.92)
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
Every source the paper cites for this claim was checked and supports it.
In the paper
“As a result, the target reference may contain information that cannot be supported by the source [198, 268].”
What the sources say
- Supportedcites [198] [198] Ankur Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, and Dipanjan Das. 2020. ToTTo: A Controlled Table-To-Text Generation Dataset. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . 1173-1186. - source
The Dataset section says that reference targets selected from web sentences may contain information that cannot be inferred from the source. The Data Annotation Process section also describes deleting phrases unsupported by table cells. (LLM, conf=0.93)
- Supportedcites [268] [268] Hongmin Wang. 2019. Revisiting Challenges in Data-to-Text Generation with Fact Grounding. In Proceedings of the 12th International Conference on Natural Language Generation . 311-322. - source
The Introduction reports that about 40% of human-written game-summary content cannot be directly mapped to the input boxscore records and draws on information beyond those inputs. Section 2.1 likewise describes reference content not licensed by the boxscore table. This supports the claim that a target reference may contain information the source does not support. (LLM, conf=0.93)
hedgedstates a possible 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.
- Supported
117 more claims · 74 with their cited sources checked
Create a free account to see all 304 claims and to verify the 2 references still open.
- Borderline: one of the tests for a substantial claim is unclear. 1
- It may state two separate claims as one. 90
- Probably not a substantial claim. 142
- 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
“Hallucination can lead to serious consequences such as incorrect or misleading code, security risks, and ethical issues [186].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [186]
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
“citation fabrication constitutes a form of extrinsic hallucination in the absence of retrieval augmentation, since the model generates references not grounded in any provided source material [4].”
From How LLMs Cite and Why It Matters: A Cross-Model Audit of Reference Fabrication in AI-Assisted Academic Writing and Methods to Detect Phantom Citations (2026) · 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
“Recent taxonomic work distinguishes at least seven cases [15,18].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [18]
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
“LLMs struggle to generate accurate and up-to-date responses on current topics, due to outdated knowledge, lack of domain-specific expertise, or hallucination13–17.”
From Leveraging long context in retrieval augmented language models for medical question answering (2025) · cites this paper as [16]
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
“Fine-tuning can enrich LLMs with domain knowledge, enhance their specific ability, improve the fairness and reliability of the outputs, and prevent certain damage caused by hallucination [26].”
From FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning (2024) · cites this paper as [26]
Experimental — accuracy not yet measured
41 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
§ Extrinsic Object Hallucination
“CHAIR (Caption Hallucination Assessment with Image Relevance) metric, which calculates what proportion of object words generated are actually in the image according to the ground truth captions.”
§ Extrinsic Object Hallucination
“CHAIR 𝑖 measures per-instance object hallucination, i.e. what fraction of object instances in each generated caption are hallucinated.”
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
§ 7.1 Hallucination Definition in Abstractive Summarization
“For instance, in Table 1, given the input article shown in the caption, an example of intrinsic hallucination is ' The Ebola vaccine was rejected by the FDA in 2019, '”
§ 2.1 Categorization
“in the abstractive summarization task from Table 1, the generated summary ' The first Ebola vaccine was approved in 2021 ' contradicts the source content”
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
§ Survey of Hallucination in Natural Language Generation
“The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation; and (3) hallucinations in large language models (LLMs)”
§ 1 INTRODUCTION
“The third part discusses this phenomenon in LLMs in Section 13.”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
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 · cited 3×
“Recently, the rapid development of NLG has captured the imagination of many thanks to the advances in deep learning technologies, especially Transformer [189]-based models like BERT [29], BART [100], GPT-2 [149], and GPT-3 [16].”
BackgroundAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
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
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
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 · cited 1×
“This work investigates the performances of GPT-3 [13], GPT-Neo/J [141], GPT-2 [105] and a T5-based model [106].”
BackgroundAdvances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference
(2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.001.0001 · Cited by 8,890
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 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
BackgroundLewis, 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 · cited 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
Background
Research works printed but not linked: 16
- [4] Joshua Albrecht and Rebecca Hwa. 2007. A Re-examination of Machine Learning Approaches for Sentence-Level MT Evaluation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics . Association for Computational Linguistics, Prague, Czech Republic, 880-887. https://aclanthology.org/P07-1111 -
- [16] Andrzej Białecki, Robert Muir, Grant Ingersoll, and Lucid Imagination. 2012. Apache lucene 4. In SIGIR 2012 workshop on open source information retrieval . 17. -
- [53] Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. Improving Factuality and Reasoning in Language Models through Multiagent Debate. In Forty-first International Conference on Machine Learning . -
- [121] Philipp Koehn and Rebecca Knowles. 2017. Six Challenges for Neural Machine Translation. In First Workshop on Neural Machine Translation . Association for Computational Linguistics, 28-39. -
- [145] Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML . -
- [149] Tian Li, Ahmad Beirami, Maziar Sanjabi, and Virginia Smith. 2020. Tilted Empirical Risk Minimization. In International Conference on Learning Representations . -
- [164] Jiasen Lu, Jianwei Yang, Dhruv Batra, and Devi Parikh. 2018. Neural Baby Talk. In CVPR . -
- [165] Yukun Ma, Khanh Linh Nguyen, Frank Z Xing, and Erik Cambria. 2020. A Survey on Empathetic Dialogue Systems. Information Fusion 64 (2020), 50-70. -
- [175] Marianna J. Martindale, Marine Carpuat, Kevin Duh, and Paul McNamee. 2019. Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation. In MTSummit . -
- [179] Kathleen McKeown. 1992. Text Generation . Cambridge University Press. -
- [209] 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. -
- [238] Hui Su, Xiaoyu Shen, Sanqiang Zhao, Zhou Xiao, Pengwei Hu, Cheng Niu, and Jie Zhou. 2020. Diversifying Dialogue Generation with Non-Conversational Text. In 58th Annual Meeting of the Association for Computational Linguistics . ACL, 7087-7097. -
- [256] Zhaopeng Tu, Yang Liu, Lifeng Shang, Xiaohua Liu, and Hang Li. 2017. Neural Machine Translation with Reconstruction. In Thirty-First AAAI Conference on Artificial Intelligence . -
- [261] Neeraj Varshney, Wenlin Yao, Hongming Zhang, Jianshu Chen, and Dong Yu. 2023. A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation. CoRR abs/2307.03987 (2023). https://doi.org/10.48550/arXiv.2307.03987 arXiv:2307.03987 - · arXiv · doi:10.48550/arxiv.2307.03987 · Paper page
- [285] Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Xiang Gao, Chris Quirk, Rik Koncel-Kedziorski, Jianfeng Gao, Hannaneh Hajishirzi, Mari Ostendorf, et al. 2021. A Controllable Model of Grounded Response Generation. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 35. 14085-14093. -
- [291] Xinnuo Xu, Ondřej Dušek, Verena Rieser, and Ioannis Konstas. 2021. AGGGEN: Ordering and Aggregating while Generating. roceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL2021) (2021). -
Cited by
Items 301–400 of 4,844
Kim, Y., Lee, J., Kim, S., Park, J., & Kim, J. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645148 · Cited by 55
Carroll, A. J., & Borycz, J. (2024) · The Journal of Academic Librarianship · doi:10.1016/j.acalib.2024.102899 · Cited by 101
Are AI language models such as ChatGPT ready to improve the care of individuals with epilepsy?
Boßelmann, C. M., Leu, C., & Lal, D. (2023) · Epilepsia · doi:10.1111/epi.17570 · Cited by 52
Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
Lin, H., Luo, Z., Gao, W. G., Ma, J., Wang, B., & Yang, R. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645381 · Cited by 149
Evaluating literature reviews conducted by humans versus ChatGPT: comparative study
Mostafapour, M., Fortier, J. H., Pacheco, K., Murray, H., & Garber, G. (2024) · JMIR AI · doi:10.2196/56537 · Cited by 55
“Clear, concise, neutral, structured, and specific prompts reduce the model’s tendency to respond with generic or off-topic responses, as well as generate an unsubstantiated or false response, also termed an AI hallucination [8].”
BackgroundHadan, H., Wang, D. M., Mogavi, R. H., Tu, J., Zhang-Kennedy, L., & Nacke, L. E. (2024) · Computers in Human Behavior: Artificial Humans · doi:10.1016/j.chbah.2024.100095 · Cited by 55
Hadi, M. U., tashi, Q. A., Qureshi, R., Shah, A., muneer, A., Irfan, M., Zafar, A., Shaikh, M. B., Akhtar, N., Wu, J., et al. (2023) · doi:10.36227/techrxiv.23589741.v3 · Cited by 53
Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
Wang, Q., Fu, Y., Cao, Y., Wang, S., Tian, Z., & Ding, L. (2023) · arXiv · doi:10.48550/arxiv.2308.15022 · Cited by 55
“Previous works (Ji et al., 2023; Bang et al., 2023) point out that many LLMs can generate nonfactual and untruthful information that cannot be verified from the inputs across tasks.”
ChatGPT hallucinating: can it get any more humanlike?
Siontis, K. C., Attia, Z. I., Asirvatham, S. J., & Friedman, P. A. (2023) · European Heart Journal · doi:10.1093/eurheartj/ehad766 · Cited by 90
Jill Watson: A Virtual Teaching Assistant Powered by ChatGPT
Taneja, K., Maiti, P., Kakar, S., Guruprasad, P., Rao, S., & Goel, A. K. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-64302-6_23 · Cited by 62
Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise
Wang, R., Ribeiro, A., Robinson, C., Loeb, S., & Demszky, D. (2024) · doi:10.21203/rs.3.rs-5363154/v1 · Cited by 53
The use of ChatGPT and other large language models in surgical science
Janssen, B. V., Kazemier, G., & Besselink, M. G. (2023) · BJS Open · doi:10.1093/bjsopen/zrad032 · Cited by 53
Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method
Zhang, X., & Gao, W. (2023) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2023.ijcnlp-main.64 · Cited by 220
Chu, C. P. (2024) · Frontiers in Veterinary Science · doi:10.3389/fvets.2024.1395934 · Cited by 83
“Hallucination, or artificial hallucination, refers to the generation of implausible but confident responses by ChatGPT, which poses a significant issue (80).”
BackgroundThe role of large language models in agriculture: harvesting the future with LLM intelligence
Shaikh, T. A., Rasool, T., Veningston, K., & Yaseen, S. M. (2024) · Progress in Artificial Intelligence · doi:10.1007/s13748-024-00359-4 · Cited by 86
“When LLMs exhibit emergent behavior that is both irrational and erroneous while having plausible semantics or syntax, this is called a hallucination [252].”
Reza, M., Laundry, N. M., Musabirov, I., Dushniku, P., Yu, Z. Y. “., Mittal, K., Grossman, T., Liut, M., Kuzminykh, A., & Williams, J. J. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641899 · Cited by 52
Event Knowledge in Large Language Models: The Gap Between the Impossible and the Unlikely
Kauf, C., Ivanova, A. A., Rambelli, G., Chersoni, E., She, J. S., Chowdhury, Z., Fedorenko, E., & Lenci, A. (2023) · Cognitive Science · doi:10.1111/cogs.13386 · Cited by 53
Gravina, A. G., Pellegrino, R., Palladino, G., Imperio, G., Ventura, A., & Federico, A. (2024) · Digestive and Liver Disease · doi:10.1016/j.dld.2024.02.019 · Cited by 52
Künzle, P., & Paris, S. (2024) · Clinical Oral Investigations · doi:10.1007/s00784-024-05968-w · Cited by 84
“This term describes their habit to convincingly state false information, which hence requires specific caution during the use of such LLMAs [24].”
BackgroundBiomedRAG: A retrieval augmented large language model for biomedicine
Li, M., Kilicoglu, H., Xu, H., & Zhang, R. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104769 · Cited by 106
Unlearn What You Want to Forget: Efficient Unlearning for LLMs
Chen, J., & Yang, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.738 · Cited by 52
Large language model for table processing: a survey
Lu, W., Zhang, J., Fan, J., Fu, Z., Chen, Y., & Du, X. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-024-40763-6 · Cited by 156
“DIN-SQL [Pourreza and Rafiei, 2023] proposes breaking down the text-to-SQL task into sub-tasks.”
Technological folie à deux: feedback loops between AI chatbots and mental health
Dohnány, S., Kurth-Nelson, Z., Spens, E., Luettgau, L., Reid, A., Gabriel, I., Summerfield, C., Shanahan, M., & Nour, M. M. (2026) · Nature Mental Health · doi:10.1038/s44220-026-00595-8 · Cited by 51
GEO: Generative Engine Optimization
Aggarwal, P., Murahari, V., Rajpurohit, T., Kalyan, A., Narasimhan, K., & Deshpande, A. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671900 · Cited by 62
“Citations are especially important given the tendency of LLMs to hallucinate information (Ji et al., 2023).”
BackgroundHsu, H.-Y., Hsu, K.-C., Hou, S.-Y., Wu, C.-L., Hsieh, Y.-W., & Cheng, Y.-D. (2023) · JMIR Medical Education · doi:10.2196/48433 · Cited by 50
“Research by Ji et al [15] has demonstrated that multiple factors contribute to the inception of these hallucinations within NLG models, but a range of methods for their mitigation have also been proposed.”
BackgroundHarnessing Large Language Models for Cognitive Assistants in Factories
Freire, S. K., Foosherian, M., Wang, C., & Niforatos, E. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3604313 · Cited by 75
“[15] differentiate intrinsic and extrinsic hallucinations in natural language generation.”
BackgroundKim, K., Cho, K., Jang, R., Kyung, S., Lee, S., Ham, S., Choi, E., Hong, G.-S., & Kim, N. (2024) · Korean Journal of Radiology · doi:10.3348/kjr.2023.0818 · Cited by 61
“Hallucinations, characterized by the generation of unrealistic or spurious outputs, challenge the credibility and reliability of generated content [140,141].”
BackgroundParadigm shifts: exploring AI's influence on qualitative inquiry and analysis
Williams, R. (2024) · Frontiers in Research Metrics and Analytics · doi:10.3389/frma.2024.1331589 · Cited by 81
AI-Generated Content (AIGC) for Various Data Modalities: A Survey
Foo, L. G., Rahmani, H., & Liu, J. (2025) · ACM Computing Surveys · doi:10.1145/3728633 · Cited by 138
“When using large language models such as ChatGPT, they also can hallucinate make factual errors [580], which can be problematic in these specialized domains.”
Moëll, B., & Aronsson, F. S. (2025) · Journal of Medical Internet Research · doi:10.2196/75849 · Cited by 71
“Key limitations relevant to medicine include: •Accuracy issues and hallucinations: LLMs can generate incorrect information (“misinformation”) or fabricate plausible-sounding but entirely false statements, citations, or data (“hallucinations”) [7].”
Human–AI collectives most accurately diagnose clinical vignettes
Zöller, N., Berger, J., Lin, I., Fu, N., Komarneni, J., Barabucci, G., Laskowski, K., Shia, V., Harack, B., Chu, E. A., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2426153122 · Cited by 98
AlphaFold 3: an unprecedent opportunity for fundamental research and drug development
Fang, Z., Ran, H., Zhang, Y., Chen, C., Ping, L., Zhang, X., & Wu, M. (2025) · Precision Clinical Medicine · doi:10.1093/pcmedi/pbaf015 · Cited by 76
“However, its existence has also caused some new problems, the most prominent of which is the phenomenon of hallucination [ 51 ].”
Still no lie detector for language models: probing empirical and conceptual roadblocks
Levinstein, B. A., & Herrmann, D. A. (2025) · Philosophical Studies · doi:10.1007/s11098-023-02094-3 · Cited by 50
“This is sometimes called lying and sometimes called hallucinating (Ji et al. 2023; Evans et al. 2021).”
Towards Autonomous Testing Agents via Conversational Large Language Models
Feldt, R., Kang, S., Yoon, J., & Yoo, S. (2023) · 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00148 · Cited by 49
“While the “error” the model did in the earlier step can be seen as a type of hallucination [22], we argue that for testing this is less severe (test code will not be part of the final, deployed software system) and can even be a benefit.”
BackgroundCobb, P. J. (2023) · Advances in Archaeological Practice · doi:10.1017/aap.2023.20 · Cited by 75
ChatGPT Hallucinates when Attributing Answers
Zuccon, G., Koopman, B., & Shaik, R. (2023) · Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region · doi:10.1145/3624918.3625329 · Cited by 51
“Hallucinations in LLMs like ChatGPT refer to the generation of factually incorrect or entirely made-up information [9].”
BackgroundLeong, J., Pataranutaporn, P., Danry, V., Perteneder, F., Mao, Y., & Maes, P. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642393 · Cited by 50
Look Before You Leap: An Exploratory Study of Uncertainty Analysis for Large Language Models
Huang, Y., Song, J., Wang, Z., Zhao, S., Chen, H., Juefei-Xu, F., & Ma, L. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3519464 · Cited by 339
“Such phenomenon of erroneous generation can exhibit in terms of different manifestations (e.g., hallucination [8], disinformation [9], bias [10]) across various tasks.”
Hipgrave, L., Goldie, J., Dennis, S., & Coleman, A. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1606291 · Cited by 51
“It also risks generating “ hallucinations, ” where the AI generates information that is incorrect, misleading, or entirely fabricated (25, 36).”
Fine-grained Hallucination Detection and Editing for Language Models
Mishra, A., Asai, A., Balachandran, V., Wang, Y., Neubig, G., Tsvetkov, Y., & Hajishirzi, H. (2024) · arXiv · doi:10.48550/arxiv.2401.06855 · Cited by 49
Sociotechnical Safety Evaluation of Generative AI Systems
Weidinger, L., Rauh, M., Marchal, N., Manzini, A., Hendricks, L. A., Mateos-Garcia, J., Bergman, S., Kay, J., Griffin, C., Bariach, B., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.11986 · Cited by 49
AirGPT: Pioneering the convergence of conversational AI with atmospheric science
Song, J., Ma, C., & Ran, M. (2025) · npj Climate and Atmospheric Science · doi:10.1038/s41612-025-01070-4 · Cited by 48
Ma, S., Chen, Q., Wang, X., Zheng, C., Peng, Z., Yin, M., & Ma, X. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713423 · Cited by 48
Hoque, M. N., Mashiat, T., Ghai, B., Shelton, C. D., Chevalier, F., Kraus, K., & Elmqvist, N. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641895 · Cited by 48
Choi, W. (2023) · BMC Medical Education · doi:10.1186/s12909-023-04832-x · Cited by 48
“A particularly problematic form of randomness is hallucination, a phenomenon where ChatGPT generates plau-sible-sounding but incorrect or misleading [22–25].”
BackgroundSystems engineering issues for industry applications of large language model
Chen, W., Yan-yi, L., Tie-zheng, G., Li, D., Tao, H., Li, Z., Yang, Q., Hui-han, W., & Ying-you, W. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.111165 · Cited by 78
Jamplate: Exploring LLM-Enhanced Templates for Idea Reflection
Xu, X. (., Yin, J., Gu, C., Mar, J., Zhang, S., E, J. L., & Dow, S. P. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645196 · Cited by 48
Shorinwa, O., Mei, Z., Lidard, J., Ren, A. Z., & Majumdar, A. (2026) · ACM Computing Surveys · doi:10.1145/3744238 · Cited by 61
Prompt engineering on leveraging large language models in generating response to InBasket messages
Yan, S., Knapp, W., Leong, A., Kadkhodazadeh, S., Das, S., Jones, V. G., Clark, R., Grattendick, D., Chen, K., Hladik, L., et al. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae172 · Cited by 47
“14,15 Detecting and mitigating hallucinations have been challenging in LLMs. Automatic detection and a benchmark of the detection of hallucinations are still not well established, and have not been widely validated in the healthcare context 16 ; human validation of hallucinations remains the gold…”
BackgroundSiderska, J., Aunimo, L., Süße, T., Stamm, J. V. (. S. )., Kedziora, D., & Aini, S. N. B. M. (2023) · Engineering Management in Production and Services · doi:10.2478/emj-2023-0030 · Cited by 111
“The technical challenges related to conversational AI are often related to hallucinations, which refer to unreliable information generated by large language models (Ji et al., 2023) and a bias and lack of data for training.”
BackgroundWu, R., Yu, C., Pan, X., Liu, Y., Zhang, N., Fu, Y., Wang, Y., Zheng, Z., Chen, L. Z., Jiang, Q., et al. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642790 · Cited by 87
Ma, Y., Zheng, S., Yang, Z., Pan, H., & Hong, J. (2025) · International Journal of Production Research · doi:10.1080/00207543.2025.2472298 · Cited by 119
“Hallucination (Ji et al. 2023).”
KernelGPT: Enhanced Kernel Fuzzing via Large Language Models
Yang, C., Zhao, Z., & Zhang, L. (2025) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3676641.3716022 · Cited by 131
“While harnessing the potential of LLMs, we must design strategies to mitigate their inherent limitations, such as context size restrictions and hallucinations [27].”
”My AI is Lying to Me”: User-reported LLM hallucinations in AI mobile apps reviews
Massenon, R., Gambo, I., Khan, J. A., Agbonkhese, C., & Alwadain, A. S. (2025) · Scientific Reports · doi:10.1038/s41598-025-15416-8 · Cited by 91
“The phenomenon of LLM hallucination, broadly defined as the generation of outputs that are nonsensical, unfaithful to source content, or factually incorrect, has become a central focus of AI research 6,8 .”
InfluentialPeer Review in the Age of Generative AI
Kankanhalli, A., & National University of Singapore (2024) · Journal of the Association for Information Systems · doi:10.17705/1jais.00865 · Cited by 47
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
Mündler, N., He, J., Jenko, S., & Vechev, M. (2023) · arXiv · doi:10.48550/arxiv.2305.15852 · Cited by 47
Language models and psychological sciences
Sartori, G., & Orrù, G. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1279317 · Cited by 91
Kozaily, E., Geagea, M., Akdogan, R. E., Atkins, J., Elshazly, M. B., Guglin, M. E., Tedford, R. J., & Wehbe, R. M. (2024) · International Journal of Cardiology · doi:10.1016/j.ijcard.2024.132115 · Cited by 61
Tozuka, R., Johno, H., Amakawa, A., Sato, J., Muto, M., Seki, S., Komaba, A., & Onishi, H. (2024) · Japanese Journal of Radiology · doi:10.1007/s11604-024-01705-1 · Cited by 81
“This phenomenon, referred to as LLM hallucinations, can generate seemingly plausible but factually incorrect information, making it difficult to rely on LLMs for clinical diagnoses [2, 5, 6].”
Do large language models resemble humans in language use?
Cai, Z. G., Duan, X., Haslett, D. A., Wang, S., & Pickering, M. J. (2023) · doi:10.31234/osf.io/s49qv · Cited by 46
Explainable depression symptom detection in social media
Bao, E., Pérez, A., & Parapar, J. (2024) · Health Information Science and Systems · doi:10.1007/s13755-024-00303-9 · Cited by 46
“LLMs can generate text unsupported by the input and produce inaccurate responses, a phenomenon called “hallucination” [82].”
BackgroundBrameier, D. T., Alnasser, A. A., Carnino, J. M., Bhashyam, A. R., von Keudell, A. G., & Weaver, M. J. (2023) · Journal of Bone and Joint Surgery · doi:10.2106/jbjs.23.00473 · Cited by 46
A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities
Tocchetti, A., Corti, L., Balayn, A., Yurrita, M., Lippmann, P., Brambilla, M., & Yang, J. (2025) · ACM Computing Surveys · doi:10.1145/3665926 · Cited by 98
Robust Multi Model RAG Pipeline For Documents Containing Text, Table & Images
Joshi, P., Gupta, A. K., Kumar, P., & Sisodia, M. S. (2024) · International Conference on Applied Artificial Intelligence and Computing (ICAAIC) · doi:10.1109/icaaic60222.2024.10574972 · Cited by 73
“However it’s apparent that these LLMs are unintendedly prone to hallucinate ( [2], [4]), which degrades the system performance and fails to generate accurate results in the field of generative AI.”
BackgroundEvaluating Generative Ad Hoc Information Retrieval
Gienapp, L., Scells, H., Deckers, N., Bevendorff, J., Wang, S., Kiesel, J., Syed, S., Fröbe, M., Zuccon, G., Stein, B., et al. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657849 · Cited by 72
Generative AI in the context of assistive technologies: Trends, limitations and future directions
Fu, B., Hadid, A., & Damer, N. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105347 · Cited by 66
Why Language Models Hallucinate
Kalai, A. T., Nachum, O., Vempala, S. S., & Zhang, E. (2025) · arXiv · doi:10.48550/arxiv.2509.04664 · Cited by 45
Brain-Inspired Remote Sensing Foundation Models and Open Problems: A Comprehensive Survey
Jiao, L., Huang, Z., Lu, X., Liu, X., Yang, Y., Zhao, J., Zhang, J., Hou, B., Yang, S., Liu, F., et al. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3316302 · Cited by 58
Large language models: a primer and gastroenterology applications
Shahab, O., Kurdi, B. E., Shaukat, A., Nadkarni, G. N., & Soroush, A. (2024) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848241227031 · Cited by 48
“3,25,26 They also cannot perform tasks that require a digit or letter-level understanding of text due to data representation choices made at the time of model training.”
Strengths, Weaknesses, Opportunities, and Threats of Using ChatGPT in Scientific Research
Giray, L., Jacob, J., & Gumalin, D. L. (2024) · International Journal of Technology in Education · doi:10.46328/ijte.618 · Cited by 44
Quo Vadis ChatGPT? From Large Language Models to Large Knowledge Models
Venkatasubramanian, V., & Chakraborty, A. (2024) · Computers and Chemical Engineering · doi:10.1016/j.compchemeng.2024.108895 · Cited by 42
“This enables one to circumvent the problems of hallucinations in LLMs[119], and augment domain-specific knowledge to LLMs, resulting in a system that does not merely recall (occasionally, incorrect) factual information from its training data[120].”
BackgroundFeng, Y., Zhou, L., Ma, C., Zheng, Y., He, R., & Li, Y. (2025) · GigaScience · doi:10.1093/gigascience/giae082 · Cited by 65
GastroBot: a Chinese gastrointestinal disease chatbot based on the retrieval-augmented generation
Zhou, Q., Liu, C., Duan, Y., Sun, K., Li, Y., Kan, H., Gu, Z., Shu, J., & Hu, J. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1392555 · Cited by 44
“Given the substantial patient population with gastrointestinal diseases and the complexity of diagnosis and treatment, the “illusions” brought about by LLMs may pose additional challenges to the diagnosis and treatment of gastrointestinal diseases (5, 7).”
BackgroundNyberg, A. J., Schleicher, D. J., Bell, B. S., Boon, C., Cappelli, P., Collings, D. G., Dalle Molle, J. E., Feuerriegel, S., Gerhart, B., Jeong, Y., et al. (2025) · Journal of Management · doi:10.1177/01492063251325188 · Cited by 47
“GenAI is also prone to random error in the form of hallucination, wherein generated content does not align with the source content (Ji, et al., 2023), which can lead to arbitrary and inaccurate decisions.”
WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences
Liu, X., Lai, H., Yu, H., Xu, Y., Zeng, A., Du, Z., Zhang, P., Dong, Y., & Tang, J. (2023) · Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599931 · Cited by 45
“• Hallucination [13]: the answer leverages the internal knowledge of LLMs instead of references, which is not factual-grounded and sometimes severely wrong.”
BackgroundSelf-citationCHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools
Ni, J., Bingler, J., Senni, C. C., Kraus, M., Gostlow, G., Schimanski, T., Stammbach, D., Vaghefi, S. A., Wang, Q., Webersinke, N., et al. (2023) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2023.emnlp-demo.3 · Cited by 85
Self-citationSchorcht, S., Buchholtz, N. F., & Baumanns, L. (2024) · Frontiers in Education · doi:10.3389/feduc.2024.1386075 · Cited by 101
Reddy, M. R., Walter, N. G., & Sevryugina, Y. V. (2024) · Journal of Chemical Education · doi:10.1021/acs.jchemed.4c00226 · Cited by 55
Performance of ChatGPT 3.5 and 4 on U.S. dental examinations: the INBDE, ADAT, and DAT
Dashti, M., Ghasemi, S., Ghadimi, N., Hefzi, D., Karimian, A., Zare, N., Fahimipour, A., Khurshid, Z., Chafjiri, M. M., & Ghaedsharaf, S. (2024) · Imaging Science in Dentistry · doi:10.5624/isd.20240037 · Cited by 53
Analysis of ChatGPT Responses to Ophthalmic Cases: Can ChatGPT Think like an Ophthalmologist?
Chen, J., Reddy, A. J., Al-Sharif, E. M., Shoji, M. K., Kalaw, F. G. P., Eslani, M., Lang, P. Z., Arya, M., Koretz, Z. A., Bolo, K. A., et al. (2024) · Ophthalmology Science · doi:10.1016/j.xops.2024.100600 · Cited by 53
“44 For example, LLMs may hallucinate psychiatric diseases such as major depressive or bipolar disorder for a patient, resulting in unnecessary and undue stigmatization.”
BackgroundThe AI Future of Emergency Medicine
Petrella, R. J. (2024) · Annals of Emergency Medicine · doi:10.1016/j.annemergmed.2024.01.031 · Cited by 43
Evaluating large language models for software testing
Li, Y., Liu, P., Wang, H., Chu, J., & Wong, W. E. (2025) · Computer Standards & Interfaces · doi:10.1016/j.csi.2024.103942 · Cited by 42
Graph Reasoning for Question Answering with Triplet Retrieval
Li, S., Gao, Y., Jiang, H., Yin, Q., Li, Z., Yan, X., Zhang, C., & Yin, B. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.208 · Cited by 42
SCOTT: Self-Consistent Chain-of-Thought Distillation
Wang, P., Wang, Z., Li, Z., Gao, Y., Yin, B., & Ren, X. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.304 · Cited by 216
Using GPT ‐4 for LI‐RADS feature extraction and categorization with multilingual free‐text reports
Gu, K., Lee, J. H., Shin, J., Hwang, J. A., Min, J. H., Jeong, W. K., Lee, M. W., Song, K. D., & Bae, S. H. (2024) · Liver International · doi:10.1111/liv.15891 · Cited by 54
“19 Due to the ‘black box’ nature of deep learning models, it can be challenging to pinpoint the exact sources of these errors.”
BackgroundBenchmarking Human–AI collaboration for common evidence appraisal tools
Woelfle, T., Hirt, J., Janiaud, P., Kappos, L., Ioannidis, J. P. A., & Hemkens, L. G. (2024) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2024.111533 · Cited by 60
Prompt Fuzzing for Fuzz Driver Generation
Lyu, Y., Xie, Y., Chen, P., & Chen, H. (2024) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3658644.3670396 · Cited by 131
“Firstly, it sanitizes programs that contain syntax errors identified by C/C++ compilers.”
Peykani, P., Ramezanlou, F., Tănăsescu, C. R., & Ghanidel, S. (2025) · Applied Sciences · doi:10.3390/app15148103 · Cited by 84
Patel, K., Shah, M., Qureshi, K. M., & Qureshi, M. R. N. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11435-z · Cited by 42
Chain-of-Verification Reduces Hallucination in Large Language Models
Dhuliawala, S., Komeili, M., Xu, J., Raileanu, R., Li, X., Celikyilmaz, A., & Weston, J. (2023) · arXiv · doi:10.48550/arxiv.2309.11495 · Cited by 42
A New Approach to Web Application Security: Utilizing GPT Language Models for Source Code Inspection
Szabó, Z., & Bilicki, V. (2023) · Future Internet · doi:10.3390/fi15100326 · Cited by 65
“…level, whereby the generated responses can be forced to behave in a factual, meaningful, non-random manner, precisely adhering to the rules passed in the prompt and excluding the so-called “hallucinations” [42], as opposed to ChatGPT, which has a significantly higher non-deterministic factor.”
Cantens, T. (2024) · AI & Society · doi:10.1007/s00146-023-01840-9 · Cited by 78
“Hallucinations are intrinsic to natural language generation models (Ji et al. 2023).”
Han, C., Kim, D. W., Kim, S., You, S. C., Park, J. Y., Bae, S., & Yoon, D. (2024) · iScience · doi:10.1016/j.isci.2024.109022 · Cited by 62
Kang, B., & Hong, M. (2025) · JMIR Medical Informatics · doi:10.2196/63538 · Cited by 66
“To tackle the inherent challenges posed by LLM variability and potential hallucinations [38] in chatbot responses, we developed a comprehensive response validation pipeline.”
Rapp, A., Lodovico, C. D., & Di, L. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2025.103471 · Cited by 79
Augmenting research methods with foundation models and generative AI
Rossi, S., Rossi, M., Mukkamala, R. R., Thatcher, J. B., & Dwivedi, Y. K. (2024) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2023.102749 · Cited by 66
HalluLens: LLM Hallucination Benchmark
Bang, Y., Ji, Z., Schelten, A., Hartshorn, A., Fowler, T., Zhang, C., Cancedda, N., & Fung, P. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.1176 · Cited by 41
Self-citationApplying sparse autoencoders to unlearn knowledge in language models
Farrell, E., Lau, Y.-T., & Conmy, A. (2024) · arXiv · doi:10.48550/arxiv.2410.19278 · Cited by 41
Leveraging generative AI for clinical evidence synthesis needs to ensure trustworthiness
Zhang, G., Jin, Q., Jered McInerney, D., Chen, Y., Wang, F., Cole, C. L., Yang, Q., Wang, Y., Malin, B. A., Peleg, M., et al. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104640 · Cited by 40
FaithDial: A Faithful Benchmark for Information-Seeking Dialogue
Dziri, N., Kamalloo, E., Milton, S., Zaiane, O., Yu, M., Ponti, E. M., & Reddy, S. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00529 · Cited by 63
“Hallucination in knowledge-grounded neural language generation has recently received increasing attention from the NLP community (Ji et al., 2022).”
Background
Metadata
- Authors
- Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- ORCID
- Venue
- ACM Computing Surveys
- Published
- 2023-03-03
- Volume
- 55
- Issue
- 12
- Pages
- 1-38
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4309674289
- Semantic Scholar
- 3def68bd0f856886d34272840a7f81588f2bc082
- Cited by
- 5,025
- References
- 111
- Citations by year
- 2026: 2296 · 2025: 1441 · 2024: 817 · 2023: 453
- FWCI
- 224.36
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- hallucinations, natural language generation, hallucination mitigation, abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, large language models, transformer models
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 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (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.




