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 401–500 of 4,844
Doctor-patient interactions in the age of AI: navigating innovation and expertise
Hryciw, B. N., Fortin, Z., Ghossein, J., & Kyeremanteng, K. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1241508 · Cited by 40
“This may in fact compromise patient autonomy and lead to ill-informed decision-making (7, 10).”
BackgroundExplainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models
Wang, H., & Shu, K. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.416 · Cited by 156
Metzger, L., Miller, L., Baumann, M., & Kraus, J. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642122 · Cited by 73
Enhancing Recommendation Diversity by Re-ranking with Large Language Models
Carraro, D., & Bridge, D. (2025) · ACM Transactions on Recommender Systems · doi:10.1145/3700604 · Cited by 101
Luo, H., Zhang, Z., Zhu, Q., Ameur, N. E. H. B., Liu, X., Fan, D., & Cai, Y. (2025) · Landscape and Urban Planning · doi:10.1016/j.landurbplan.2025.105323 · Cited by 60
Tang, Y., Situ, J., Cui, A. Y., Wu, M., & Huang, Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714224 · Cited by 79
Generative AI risks and resilience: How users adapt to hallucination and privacy challenges
Lee, C., Kim, J., Lim, J. S., & Shin, D. (2025) · Telematics and Informatics Reports · doi:10.1016/j.teler.2025.100221 · Cited by 74
Li, H., Fu, J., & Python, A. (2025) · Journal of Medical Internet Research · doi:10.2196/71916 · Cited by 69
“Third, while LLMs can generate human-preferred, coherent, and credible language outputs, these can be fabricated or inaccurate, a phenomenon known as “hallucination” [111].”
Agentic LLMs in the supply chain: towards autonomous multi-agent consensus-seeking
Jannelli, V., Schoepf, S., Bickel, M., Netland, T. H., & Brintrup, A. M. (2025) · International Journal of Production Research · doi:10.1080/00207543.2025.2604311 · Cited by 124
ChatGPT Hallucinates Non-existent Citations: Evidence from Economics
Buchanan, J., Hill, S., & Shapoval, O. (2024) · The American Economist · doi:10.1177/05694345231218454 · Cited by 40
“Ji et al. (2023) warn that, “ Hallucination … is concerning because it hinders performance and raises safety concerns for real-world applications.”
BackgroundYan, L., Zhao, L., Echeverria, V., Jin, Y., Alfredo, R., Li, X., Gaševi’c, D., & Martinez-Maldonado, R. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-64299-9_13 · Cited by 40
Zhang, T., Koutsoumpis, A., Oostrom, J. K., Holtrop, D., Ghassemi, S., & de Vries, R. E. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3374875 · Cited by 66
“AlthoughLLMsarefine-tunedusingReinforcementLearningfromHumanFeedback (RLHF)[9],theyarestillunsupervisedgenerativemodels,in-steadofsuperviseddiscriminativemodels,thatcansufferfrom “hallucinations” [9], [11] (i.e., provide unreliable information).”
Safeguarding human values: rethinking US law for generative AI’s societal impacts
Cheong, I., Caliskan, A., & Kohno, T. (2024) · AI and Ethics · doi:10.1007/s43681-024-00451-4 · Cited by 86
“The significant achievement of generative AI is its ability to “complete sentences” and produce various forms of human-like creative work [83], including even unintended results [2, 5].”
Generative AI in Education: Technical Foundations, Applications, and Challenges
Rashid, S. F., Duong‐Trung, N., & Pinkwart, N. (2024) · Artificial intelligence · doi:10.5772/intechopen.1005402 · Cited by 71
Generative Artificial Intelligence in Pathology and Medicine: A Deeper Dive
Rashidi, H. H., Pantanowitz, J., Chamanzar, A., Fennell, B. D., Wang, Y., Gullapalli, R. R., Tafti, A. P., Deebajah, M., Albahra, S., Glassy, E. F., et al. (2024) · Modern Pathology · doi:10.1016/j.modpat.2024.100687 · Cited by 56
Large language models hallucination: A comprehensive survey
Alansari, A., & Luqman, H. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100970 · Cited by 259
The Crowdless Future? Generative AI and Creative Problem Solving
Boussioux, L., N. Lane, J., Zhang, M., Jacimovic, V., & Lakhani, K. R. (2023) · doi:10.2139/ssrn.4533642 · Cited by 343
Hallucination to truth: a review of fact-checking and factuality evaluation in large language models
Rahman, S. S., Islam, M. A., Alam, M. M., Zeba, M., Rahman, M. A., Chowa, S. S., Raiaan, M. A. K., & Azam, S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11454-w · Cited by 39
“To test interactive evidence retrieval and conversational-based fact-checking in multi-turn RAG pipelines, dialogue datasets are used [54, 63].”
InfluentialExploring AI-Generated Text in Student Writing: How Does AI Help?
Woo, D. J., Susanto, H., Yeung, C. H., Guo, K., & Fung, A. K. Y. (2023) · arXiv · doi:10.48550/arxiv.2304.02478 · Cited by 39
MENLI: Robust Evaluation Metrics from Natural Language Inference
Chen, Y., & Eger, S. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00576 · Cited by 115
“may be considered special cases) is a particular worrisome limitation of recent large language models (Ji et al., 2022).”
BackgroundLa inteligencia artificial generativa y la educación universitaria: ¿Salió el genio de la lámpara?
Mendiola, M. S., & Carbajal-Degante, E. (2023) · Perfiles Educativos · doi:10.22201/iisue.24486167e.2023.especial.61692 · Cited by 141
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
Yang, F., Zhao, P., Wang, Z., Wang, L., Qiao, B., Zhang, J., Garg, M., Lin, Q., Rajmohan, S., & Zhang, D. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-industry.29 · Cited by 104
PMET: Precise Model Editing in a Transformer
Li, X., Li, S., Song, S., Yang, J., Ma, J., & Yu, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29818 · Cited by 44
Applicability of large language models and generative models for legal case judgement summarization
Deroy, A., Ghosh, K., & Ghosh, S. (2024) · Artificial Intelligence and Law · doi:10.1007/s10506-024-09411-z · Cited by 96
“…in Large language models and Extractive Summarization models: Hallucinations are a serious pitfall of LLMs and other natural language generation models (including abstractive text summarization models) as they may generate content which is non-factual and sometimes irrelevant to the context [33].”
BackgroundSelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Manakul, P., Liusie, A., & Gales, M. J. F. (2023) · arXiv · doi:10.48550/arxiv.2303.08896 · Cited by 38
Relatedly: Scaffolding Literature Reviews with Existing Related Work Sections
Palani, S., Naik, A., Downey, D., Zhang, A. X., Bragg, J., & Chang, J. C. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580841 · Cited by 59
“ity check since generation models are often prone to these issues, especially hallucinations [31].”
BackgroundGenerative AI models should include detection mechanisms as a condition for public release
Knott, A., Pedreschi, D., Chatila, R., Chakraborti, T., Leavy, S., Baeza-Yates, R., Eyers, D., Trotman, A., Teal, P. D., Biecek, P., et al. (2023) · Ethics and Information Technology · doi:10.1007/s10676-023-09728-4 · Cited by 34
“…is a citizen receiving the text as professional advice from her doctor or lawyer, she may want to know how thoroughly it has been checked for errors, given the known problems of errors in FM output (e.g., Ji et al., 2023) and overreliance on FM output by human operators (e.g., Wang et al., 2023).”
BackgroundMorreel, S., Verhoeven, V., & Mathysen, D. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000349 · Cited by 37
McCoy, L. G., Ng, F. Y. C., Sauer, C. M., Legaspi, K. E. Y., Jain, B., Gallifant, J., McClurkin, M., Hammond, A., Goode, D., Gichoya, J. W., et al. (2024) · BMC Medical Education · doi:10.1186/s12909-024-06048-z · Cited by 63
“LLMs are also prone to so-called “hallucinations”, wherein plausible-sounding but incorrect results are generated with apparent confidence [18, 19], including at times the generation and citation of completely fabricated scientific literature.”
BackgroundRobot learning in the era of foundation models: a survey
Xiao, X., Liu, J., Wang, Z., Zhou, Y., Qi, Y., Jiang, S., He, B., & Cheng, Q. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129963 · Cited by 91
AI Alignment: A Contemporary Survey
Ji, J., Qiu, T., Chen, B., Zhou, J., Zhang, B., Hong, D., Lou, H., Wang, K., Duan, Y., He, Z., et al. (2025) · ACM Computing Surveys · doi:10.1145/3770749 · Cited by 815
Zhao, S., Yang, H., Kareck, T. L., Khan, F. I., & Wang, Q. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.112159 · Cited by 62
Almanac: Retrieval-Augmented Language Models for Clinical Medicine
Hiesinger, W., Zakka, C., Chaurasia, A., Shad, R., Dalal, A., Kim, J., Moor, M., Alexander, K., Ashley, E., Boyd, J., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-2883198/v1 · Cited by 36
“However, due the nature of their training objective— predicting the next token in a sentence—large language models (LLMs) can be prone to generating factually incorrect statements, a phenomenon commonly known as hallucination [8, 9].”
BackgroundYang, Z., Yao, Z., Tasmin, M., Vashisht, P., Jang, W. S., Ouyang, F., Wang, B., Berlowitz, D., & Yu, H. (2023) · medRxiv · doi:10.1101/2023.10.26.23297629 · Cited by 36
“48 We found that more than 18% of GPT-4V explanations contain hallucinations.”
BackgroundRHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
Ji, Z., Liu, Z., Lee, N., Yu, T., Wilie, B., Zeng, M., & Fung, P. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.275 · Cited by 37
Self-citationFighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation
Lucas, J., Uchendu, A., Yamashita, M., Lee, J., Rohatgi, S., & Lee, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.883 · Cited by 37
False authorship: an explorative case study around an AI-generated article published under my name
Spinellis, D. (2025) · Research Integrity and Peer Review · doi:10.1186/s41073-025-00165-z · Cited by 37
“Furthermore, machine-generated articles pollute the scientific communication landscape with trite platitudes, potentially incorrect facts [16], biased or discriminatory text ([17], p. 33), and often incorrect citations [18].”
Do Language Models Know When They’re Hallucinating References?
Agrawal, A., Suzgun, M., Mackey, L., & Kalai, A. (2024) · Findings of the Association for Computational Linguistics: EACL 2024 · doi:10.18653/v1/2024.findings-eacl.62 · Cited by 37
Do Language Models Know When They’re Hallucinating References?
Agrawal, A., Suzgun, M., Mackey, L., & Kalai, A. T. (2023) · arXiv · doi:10.48550/arxiv.2305.18248 · Cited by 37
Bibliographic Research with ChatGPT may be Misleading: The Problem of Hallucination
Metze, K., Morandin-Reis, R. C., Lorand-Metze, I., & Florindo, J. B. (2024) · Journal of Pediatric Surgery · doi:10.1016/j.jpedsurg.2023.08.018 · Cited by 40
Chlorogiannis, D.-D., Apostolos, A., Chlorogiannis, A., Palaiodimos, L., Giannakoulas, G., Pargaonkar, S., Xesfingi, S., & Kokkinidis, D. G. (2023) · Healthcare · doi:10.3390/healthcare11212906 · Cited by 37
“In this context, one of the main limitations of the language-based system is the hallucination bias, where the system reports a scientifically sound answer that cannot be realistically implemented [29].”
BackgroundHow Do Analysts Understand and Verify AI-Assisted Data Analyses?
Gu, K., Shang, R., Althoff, T., Wang, C., & Drucker, S. M. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642497 · Cited by 37
“1) [41, 63, 110] or make seemingly correct erroneous outputs [11, 40].”
PANDALens: Towards AI-Assisted In-Context Writing on OHMD During Travels
Cai, R., Janaka, N., Chen, Y., Wang, L., Zhao, S., & Liu, C. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642320 · Cited by 36
An Activity System-based Perspective of Generative AI: Challenges and Research Directions
Nah, F. F., Cai, J., Zheng, R., & Pang, N. L.-S. (2023) · AIS Transactions on Human-Computer Interaction · doi:10.17705/1thci.00190 · Cited by 60
Can GPT-3.5 generate and code discharge summaries?
Falis, M., Gema, A. P., Dong, H., Daines, L., Basetti, S., Holder, M., Penfold, R., Birch, A., & Alex, B. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae132 · Cited by 59
“18 Writing and coding discharge summaries require extensive background knowledge making it of interest to explore an LLM’s capability of reading, coding, and generating discharge summaries.”
BackgroundChatGPT and Beyond: Exploring the Responsible Use of Generative AI in the Workplace
Söllner, M., Arnold, T., Benlian, A., Bretschneider, U., Knight, C., Ohly, S., Rudkowski, L., Schreiber, G., & Wendt, D. H. (2025) · Business & Information Systems Engineering · doi:10.1007/s12599-025-00932-8 · Cited by 80
“One of the key challenges from a computer science perspective lies in GenAI’s inherent tendency towards hallucination (Ji et al. 2023).”
Challenges and standardisation strategies for sensor-based data collection for digital phenotyping
Alam, N. B., Surani, M., Das, C. K., Giacco, D., Singh, S. P., & Jilka, S. (2025) · Communications Medicine · doi:10.1038/s43856-025-01013-3 · Cited by 50
“For example, LLMs such as Generative Pretrained Transformers (GPT) and Bidirectional Encoder Representations from Transformers (BERT) variants have been shown to detect depressive or anxious language patterns with high sensitivity 61,62 .”
Risks of AI scientists: prioritizing safeguarding over autonomy
Tang, X., Jin, Q., Zhu, K., Yuan, T., Zhang, Y., Zhou, W., Qu, M., Zhao, Y., Tang, J., Zhang, Z., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-63913-1 · Cited by 51
“Nevertheless, the following vulnerabilities exist: Lack of Awareness of Risks in Long-term Planning: Agents often struggle to fully comprehend and account for the potential risks associated with their long-term plans of action.”
Enhancing Accuracy in Large Language Models Through Dynamic Real-Time Information InjectionPreprint
Ouyang, Q., Wang, S., & Wang, B. (2023) · Preprints.org · doi:10.20944/preprints202312.1987.v1 · Cited by 45
Lee, Y., Son, K., Kim, T. S., Kim, J., Chung, J. J. Y., Adar, E., & Kim, J. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3662681 · Cited by 36
The Emerging Social Status of Generative AI: Vocabularies of AI Competence in Public Discourse
Bran, E., Rughiniş, C., Nadoleanu, G., & Flaherty, M. G. (2023) · 2023 24th International Conference on Control Systems and Computer Science (CSCS) · doi:10.1109/cscs59211.2023.00068 · Cited by 36
Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding
Toma, A., Lawler, P. R., Ba, J., Krishnan, R. G., Rubin, B. B., & Wang, B. (2023) · arXiv · doi:10.48550/arxiv.2305.12031 · Cited by 36
Bui, T., Tran, O., Nguyen, P., Ho, B., Nguyen, L., Bui, T., & Quan, T. (2024) · Proceedings of the 1st ACM Workshop on AI-Powered Q&A Systems for Multimedia · doi:10.1145/3643479.3662055 · Cited by 35
Hassan, A. E., Lin, D., Rajbahadur, G. K., Gallaba, K., Cogo, F. R., Chen, B., Zhang, H., Thangarajah, K., Oliva, G., Lin, J. (., et al. (2024) · Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering · doi:10.1145/3663529.3663849 · Cited by 35
“• Hallucination Limitations : FMs are prone to hallucination and can confidently generate factually wrong responses [46].”
Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
Saha, B., Saha, U., & Malik, M. Z. (2024) · IEEE Access · doi:10.1109/access.2024.3513155 · Cited by 85
On large language models safety, security, and privacy: A survey
Zhang, R., Li, H., Qian, X., Jiang, W., & Chen, H.-X. (2025) · Journal of Electronic Science and Technology · doi:10.1016/j.jnlest.2025.100301 · Cited by 66
HaluCheck: Explainable and verifiable automation for detecting hallucinations in LLM responses
Heo, S., Son, S., & Park, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126712 · Cited by 68
Proposed Framework for Human-like Language Processing of ChatGPT in Academic Writing
Mahyoob, M., Algaraady, J., & Alblwi, A. (2023) · International Journal of Emerging Technologies in Learning (iJET) · doi:10.3991/ijet.v18i14.41725 · Cited by 35
Accuracy of Vitreoretinal Disease Information From an Artificial Intelligence Chatbot
Caranfa, J. T., Bommakanti, N. K., Young, B. K., & Zhao, P. Y. (2023) · JAMA Ophthalmology · doi:10.1001/jamaophthalmol.2023.3314 · Cited by 34
Artificial Intelligence and the Simulationists
Rodgers, D. L., Needler, M., Robinson, A., Barnes, R., Brosche, T., Hernandez, J., Poore, J., VandeKoppel, P., & Ahmed, R. (2023) · Simulation in Healthcare: The Journal of the Society for Simulation in Healthcare · doi:10.1097/sih.0000000000000747 · Cited by 34
AutoKG: Efficient Automated Knowledge Graph Generation for Language Models
Chen, B., & Bertozzi, A. L. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386454 · Cited by 78
“On one hand, LLMs exhibit a tendency for ’hallucinations’ [7], [8], providing plausible yet nonfactual predictions.”
BackgroundKeith, M. J., Keiller, E., Windows-Yule, C., Kings, I., & Robbins, P. T. (2025) · Education for Chemical Engineers · doi:10.1016/j.ece.2025.01.002 · Cited by 58
Unveiling GPT-4V's hidden challenges behind high accuracy on USMLE questions: Observational Study
Yang, Z., Yao, Z., Tasmin, M., Vashisht, P., Jang, W. S., Ouyang, F., Wang, B., McManus, D. D., Berlowitz, D. R., & Yu, H. Q. (2025) · Journal of Medical Internet Research · doi:10.2196/65146 · Cited by 51
“Another significant drawback of GPT-4V involved its tendency to produce factually inaccurate responses, a problem often referred to as the hallucination effect, which is prevalent among many LLMs such as GPT-4V [38].”
Know Your Limits: A Survey of Abstention in Large Language Models
Wen, B., Yao, J., Feng, S., Xu, C., Tsvetkov, Y., Howe, B., & Wang, L. L. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00754 · Cited by 56
Knowledge graph-extended retrieval augmented generation for question answering
Linders, J., & Tomczak, J. M. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06885-5 · Cited by 40
Dissecting Corporate Culture Using Generative AI – Insights from Analyst ReportsPreprint
Li, K., Mai, F., Shen, R., Yang, C., & Zhang, T. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4558295 · Cited by 34
A Conceptual Design Method Based on Concept–Knowledge Theory and Large Language Models
Chen, L., Xia, D., Jiang, Z., Tan, X., Sun, L., & Zhang, L. (2024) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4066773 · Cited by 36
Large Language Model Supply Chain: A Research Agenda
Wang, S., Zhao, Y., Hou, X., & Wang, H. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3708531 · Cited by 126
Next Generation XR Systems—Large Language Models Meet Augmented and Virtual Reality
Afzal, M. Z., Ali, S. A., Stricker, D., Eisert, P., Hilsmann, A., Pérez-Marcos, D., Bianchi, M., Crottaz‐Herbette, S., Ioris, R. D., Mangina, E., et al. (2025) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2025.3548554 · Cited by 41
“…to the prompt, which does not scale well; 13 2) hallucinations: they can generate untruthful answers, as generations are not veri fi ed to be true; 14 and 3) lack of grounding to the real world: as they have only seen text, their output and reasoning capabilities cannot be anchored in real-world…”
Kourani, H., Berti, A., Schuster, D., & van der Aalst, W. M. P. (2025) · Software & Systems Modeling · doi:10.1007/s10270-025-01318-w · Cited by 105
McDonald, D., Papadopoulos, R., & Benningfield, L. (2024) · doi:10.36227/techrxiv.171665607.76504195/v1 · Cited by 68
Future Shock: Generative AI and the International AI Policy and Governance Crisis
Leslie, D., & Perini, A. M. (2024) · Harvard Data Science Review · doi:10.1162/99608f92.88b4cc98 · Cited by 33
Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness
Chen, J., & Mueller, J. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.283 · Cited by 33
“Accessed via black-box APIs (via providers like OpenAI/Anthropic), today’s best LLMs have been trained to produce convincing-looking responses and thus often appear overconfident (Ji et al., 2023).”
AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation
Murali, V., Maddila, C., Ahmad, I., Bolin, M., Cheng, D., Ghorbani, N., Fernandez, R., Nagappan, N., & Rigby, P. C. (2023) · arXiv · doi:10.48550/arxiv.2305.12050 · Cited by 33
Medical Hallucinations in Foundation Models and Their Impact on Healthcare
Kim, Y., Jeong, H., Chen, S., Li, S. S., Park, C., Lu, M., Alhamoud, K., Mun, J., Grau, C., Jung, M., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.05777 · Cited by 33
Kenthapadi, K., Sameki, M., & Taly, A. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671467 · Cited by 36
A review of ophthalmology education in the era of generative artificial intelligence
Heinke, A., Radgoudarzi, N., Huang, B. B., & Baxter, S. L. (2024) · Asia-Pacific Journal of Ophthalmology · doi:10.1016/j.apjo.2024.100089 · Cited by 49
Li, J., Li, J., Guo, Y., Yang, L., Chi, H., & Yang, L. (2025) · Drones · doi:10.3390/drones9040238 · Cited by 66
“Hallucination is one of the inherent limitations of LLMs, referring to cases where the model generates outputs that are inconsistent with the real world or entirely incorrect after receiving input [64,138,139].”
Atallah, S. B., Banda, N. R., Banda, A., & Roeck, N. A. (2023) · Techniques in Coloproctology · doi:10.1007/s10151-023-02837-8 · Cited by 40
“Modern LLMs do not always get it right and on occasion produce fluent and grammatically correct textual outputs that are categorically false, and in some instances fictitious—a phenomenon known as “hallucination” [39].”
BackgroundLim, J. S., Shin, D., Lee, C., Kim, J., & Zhang, J. (2025) · Journal of Broadcasting & Electronic Media · doi:10.1080/08838151.2025.2487679 · Cited by 32
Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf
Xu, Y., Wang, S., Li, P., Luo, F., Wang, X., Liu, W., & Liu, Y. (2023) · arXiv · doi:10.48550/arxiv.2309.04658 · Cited by 32
“Firstly, hallucinations (Ji et al., 2023) affect the factuality of the generated content and may negatively impact the reasoning abilities.”
BackgroundSelf-citationFactuality Challenges in the Era of Large Language Models
Augenstein, I., Baldwin, T., Cha, M., Chakraborty, T., Ciampaglia, G. L., Corney, D., DiResta, R., Ferrara, E., Hale, S., Halevy, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.05189 · Cited by 32
KI-MAG: A knowledge-infused abstractive question answering system in medical domain
Zafar, A., Sahoo, S. K., Bhardawaj, H., Das, A., & Ekbal, A. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.127141 · Cited by 39
An AI-Resilient Text Rendering Technique for Reading and Skimming Documents
Gu, Z., Arawjo, I., Li, K., Kummerfeld, J. K., & Glassman, E. L. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642699 · Cited by 31
Do people trust humans more than ChatGPT?
Buchanan, J. A., & Hickman, W. (2024) · Journal of Behavioral and Experimental Economics · doi:10.1016/j.socec.2024.102239 · Cited by 62
Cantini, R., Cosentino, C., Marozzo, F., Talia, D., & Trunfio, P. (2024) · Online Social Networks and Media · doi:10.1016/j.osnem.2024.100295 · Cited by 62
Li, K., Lacson, R. C., Guenette, J. P., DiPiro, P. J., Burk, K. S., Kapoor, N., Salah, F., & Khorasani, R. (2025) · American Journal of Roentgenology · doi:10.2214/ajr.24.32341 · Cited by 36
Student (Mis)Use of Generative AI Tools for University-Related Tasks
Reiter, L., Jörling, M., Fuchs, C., Working group ‘Artificial Intelligence in Higher Education’, & Böhm, R. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2462083 · Cited by 65
“In addition, generative AI can produce incorrect content that is unsup-ported by the training data (Ji et al., 2023), which may result in students learning incorrect information when relying on generative AI (Bentley et al., 2023).”
Harvey, E., Koenecke, A., & Kizilcec, R. F. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713210 · Cited by 86
Utilization of Generative AI-drafted Responses for Managing Patient-Provider Communication
Mandal, S., Wiesenfeld, B. M., Szerencsy, A. C., Small, W. R., Major, V. J., Richardson, S. I., Schoenthaler, A., Mann, D., & Nov, O. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01972-w · Cited by 40
Goel, I., Bhaskar, Y., Kumar, N., Singh, S., Amanullah, M., Dhar, R., & Karmakar, S. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1550407 · Cited by 31
“Additionally, these models are prone to hallucinations — generating fabricated or inaccurate outputs — and often lack real-time updates, which can compromise their reliability and safety in fast-paced, dynamic clinical environments (203).”
Language models for materials discovery and sustainability: Progress, challenges, and opportunities
Pei, Z., Yin, J., & Zhang, J. (2025) · Progress in Materials Science · doi:10.1016/j.pmatsci.2025.101495 · Cited by 30
Drosos, I., Sarkar, A., Xu, X., Negreanu, C., Rintel, S., & Tankelevitch, L. (2024) · Proceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Interaction for Work · doi:10.1145/3663384.3663389 · Cited by 30
Buholayka, M., Zouabi, R., & Tadinada, A. (2023) · Cureus · doi:10.7759/cureus.39386 · Cited by 30
“Artificial hallucination is defined as “generated content that is nonsensical or unfaithful to the provided source content” [10].”
BackgroundHo, W. L. J., Koussayer, B., & Sujka, J. (2023) · Surgery in Practice and Science · doi:10.1016/j.sipas.2023.100185 · Cited by 30
Chervonski, E., Harish, K. B., Rockman, C. R., Sadek, M., Teter, K., Jacobowitz, G. R., Berland, T. L., Lohr, J. M., Moore, C. M., & Maldonado, T. S. (2024) · Vascular · doi:10.1177/17085381241240550 · Cited by 35
McIntosh, T. R., Sušnjak, T., Liu, T., et al. (2024) · Figshare · doi:10.26181/26210234.v1 · Cited by 30
Eroğlu, Z. T., Babayiğit, O., Şen, D. Ö., & Yarkaç, F. U. (2024) · Clinical Oral Investigations · doi:10.1007/s00784-024-05799-9 · Cited by 35
“However, a notable limitation is the possibility of providing confident yet incorrect responses, known as hallucinations, especially in technical fields, such as medicine [21].”
BackgroundThe long but necessary road to responsible use of large language models in healthcare research
Kwong, J. C. C., Wang, S., Nickel, G., Cacciamani, G. E., & Kvedar, J. C. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01180-y · Cited by 49
Kefeli, J., Berkowitz, J., Cortina, J. M. A., Tsang, K. K., & Tatonetti, N. P. (2024) · Nature Communications · doi:10.1038/s41467-024-53190-9 · Cited by 53
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.




