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 201–300 of 4,844
Davidsson, P., & Sufyan, M. (2023) · Journal of Business Venturing Insights · doi:10.1016/j.jbvi.2023.e00413 · Cited by 125
Izadi, S., & Forouzanfar, M. (2024) · AI · doi:10.3390/ai5020041 · Cited by 140
“The growing body of work surveying hallucination in natural language generation provides valuable insights into the causes and potential solutions for this phenomenon [64].”
BackgroundText2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Text
Mihindukulasooriya, N., Tiwari, S. M., Enguix, C. F., & Lata, K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47243-5_14 · Cited by 185
Antaki, F., Milad, D., Chia, M. A., Giguère, C.-É., Touma, S., El-Khoury, J., Keane, P. A., & Duval, R. (2024) · British Journal of Ophthalmology · doi:10.1136/bjo-2023-324438 · Cited by 83
“18 20 Practically, hallucinations can be hard to detect due to the phenomenon of ‘automation bias’.”
InfluentialMcIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., Nowrozy, R., & Halgamuge, M. N. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103964 · Cited by 84
“A critical issue is content hallucination, where LLMs generate plausible but factually incorrect information, which can have serious implications for cybersecurity, particularly in areas such as threat intelligence and incident response, where accuracy is paramount [26, 23].”
BackgroundInfluentialExploring Human-Like Translation Strategy with Large Language Models
He, Z., Liang, T., Jiao, W., Zhang, Z., Yang, Y., Wang, R., Tu, Z., Shi, S., & Wang, X. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00642 · Cited by 97
“Hallucination issue in natural language generation (NLG) refers to the phenomenon where the content generated by the model is nonsensical or unfaithful to the provided source content [24, 12, 42, 47, 66, 21].”
BackgroundInterpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models
Louis, A., DIJCK, G. V., & Spanakis, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i20.30232 · Cited by 252
Scientific evidence for clinical text summarization using large language models: scoping review
Bednarczyk, L., Reichenpfader, D., Gaudet-Blavignac, C., Ette, A. K., Zaghir, J., Zheng, Y., Bensahla, A., Bjelogrlic, M., & Lovis, C. (2025) · Journal of Medical Internet Research · doi:10.2196/68998 · Cited by 83
“While recent studies have attempted to establish taxonomies for hallucinations [79,80], failures may be inherently task-specific, underscoring the need for systematic error analysis and categorization based on existing research.”
Xiao, T., & Xu, P. (2024) · Energy and Buildings · doi:10.1016/j.enbuild.2024.114691 · Cited by 95
Plevris, V., Papazafeiropoulos, G., & Jiménez Rios, A. (2023) · AI · doi:10.3390/ai4040048 · Cited by 81
“The term “hallucination” [21] describes the phenomenon where AI systems generate outputs that are unrealistic, incorrect, or nonsensical.”
BackgroundExploring the generative AI adoption in service industry: A mixed-method analysis
Gupta, R., & Rathore, B. (2024) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2024.103997 · Cited by 95
Leveraging long context in retrieval augmented language models for medical question answering
Zhang, G., Xu, Z., Jin, Q., Chen, F., Fang, Y., Liu, Y., Rousseau, J. F., Xu, Z., Lu, Z., Weng, C., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01651-w · Cited by 81
Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models
Yang, K.-C., & Menczer, F. (2025) · Proceedings of the 17th ACM Web Science Conference 2025 · doi:10.1145/3717867.3717903 · Cited by 81
“Despite such advantages, the additional LLM components could introduce new problems (Memon and West 2024) because language models face critical technical challenges, such as hallucinations (Ji et al. 2023), and exhibit various biases (Gallegos et al. 2024).”
ChatDev: Communicative Agents for Software Development
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.07924 · Cited by 81
Implementing Artificial Intelligence in Critical Care Medicine: a consensus of 22.
Cecconi, M., Greco, M., Shickel, B., Angus, D. C., Bailey, H., Bignami, E., Calandra, T., Celi, L. A., Einav, S., Elbers, P., et al. (2025) · Critical Care · doi:10.1186/s13054-025-05532-2 · Cited by 80
Calibrated Language Models Must Hallucinate
Kalai, A. T., & Vempala, S. S. (2024) · Proceedings of the 56th Annual ACM Symposium on Theory of Computing · doi:10.1145/3618260.3649777 · Cited by 91
Buehler, M. J. (2024) · ACS Engineering Au · doi:10.1021/acsengineeringau.3c00058 · Cited by 82
Schopow, N., Osterhoff, G., & Baur, D. (2023) · JMIR Medical Informatics · doi:10.2196/48933 · Cited by 80
“Furthermore, while able to generate plausible-sounding outputs, they may occasionally produce nonsensical or incorrect results (called “artificial hallucination”), which emphasizes the need for careful interpretation [original: McCoy et al. 2019] (new [18]) .”
BackgroundRetrieval-Augmented Generation (RAG)
Klesel, M., & Wittmann, H. F. (2025) · Business & Information Systems Engineering · doi:10.1007/s12599-025-00945-3 · Cited by 92
“This type of answer has been termed hallucination (Maynez et al. 2020; Ji et al. 2023), which is defined as ‘‘ content that is inconsistent with real-world facts or user inputs ’’ (Ji et al. 2023, p. 1).”
Zhang, X., Zhang, P., Shen, Y., Liu, M., Wang, Q., Gašević, D., & Fan, Y. (2024) · Frontiers of Digital Education · doi:10.1007/s44366-024-0028-5 · Cited by 83
Limitations of large language models in clinical problem-solving arising from inflexible reasoning
Kim, J., Podlasek, A., Shidara, K., Liu, F., Alaa, A., & Bernardo, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-22940-0 · Cited by 78
“The shortcomings of LLMs in medical reasoning and propensity to hallucinate, as demonstrated here, aligns with prior work demonstrating similar limitations across various domains [42, 16, 17, 18, 19, 21] and raises concerns regarding their trustworthiness in medical contexts[43, 44].”
Investigating ChatGPT’s Potential to Assist in Requirements Elicitation Processes
Ronanki, K., Berger, C., & Horkoff, J. (2023) · Euromicro Conference on Software Engineering and Advanced Applications (SEAA) · doi:10.1109/seaa60479.2023.00061 · Cited by 159
“Natural Language Generation (NLG) is a process that we use to generate meaningful phrases, sentences, and paragraphs in natural human language [19], and is considered one of the most critical yet complex sub-fields of NLP [14].”
BackgroundMitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based Retrofitting
Guan, X., Liu, Y., Lin, H., Lu, Y., He, B., Han, X., & Sun, L. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29770 · Cited by 215
Griewing, S., Gremke, N., Wagner, U., Lingenfelder, M., Kuhn, S., & Boekhoff, J. (2023) · Journal of Personalized Medicine · doi:10.3390/jpm13101502 · Cited by 77
“Regarding the notion of misalignment and hallucination, research recognizes a major challenge for LLMs, which tend to hallucinate unintended text, limiting their current level of development for use in real-world scenarios [27].”
BackgroundFrontier AI Regulation: Managing Emerging Risks to Public Safety
Anderljung, M., Barnhart, J., Korinek, A., Leung, J., O'Keefe, C., Whittlestone, J., Avin, S., Brundage, M., Bullock, J., Cass-Beggs, D., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.03718 · Cited by 77
AI literacy for ethical use of chatbot: Will students accept AI ethics?
Kajiwara, Y., & Kawabata, K. (2024) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2024.100251 · Cited by 147
Benefits, limits, and risks of ChatGPT in medicine
Tangsrivimol, J. A., Darzidehkalani, E., Virk, H. U. H., Wang, Z., Egger, J., Wang, M., Hacking, S., Glicksberg, B. S., Strauss, M., & Krittanawong, C. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1518049 · Cited by 76
“As the use of ChatGPT in article writing continues to grow, the emergence of artificial hallucination becomes a potential concern (Alkaissi and McFarlane, 2023; Ji et al., 2023; Gao et al., 2023).”
Large Language Models for Education: Grading Open-Ended Questions Using ChatGPT
Pinto, G., Cardoso-Pereira, I., Monteiro, D., Lucena, D., Souza, A., & Gama, K. (2023) · Proceedings of the XXXVII Brazilian Symposium on Software Engineering · doi:10.1145/3613372.3614197 · Cited by 76
“5, relying solely on ChatGPT’s corrections may be insufficient, as it can exhibit hallucinations, meaning it provides false or distorted insights generated by the model itself [7].”
BackgroundMethodYan, L., Martinez-Maldonado, R., Jin, Y., Echeverria, V., Milesi, M., Fan, J., Zhao, L., Alfredo, R., Li, X., & Gašević, D. (2025) · Computers & Education · doi:10.1016/j.compedu.2025.105322 · Cited by 85
Black-Box Access is Insufficient for Rigorous AI Audits
Casper, S., Ezell, C., Siegmann, C., Kolt, N., Curtis, T. L., Bucknall, B., Haupt, A., Wei, K., Scheurer, J., Hobbhahn, M., et al. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3659037 · Cited by 86
The mechanisms of AI hype and its planetary and social costs
Markelius, A., Wright, C., Kuiper, J., Delille, N., & Kuo, Y.-T. (2024) · AI and Ethics · doi:10.1007/s43681-024-00461-2 · Cited by 76
“…today’s generative content tools are prone to hallucinations wherein generated text “is nonsensical, or unfaithful to the provided source input” [143] but also presented as confidently as accurate text generation, “Similar to psychological hallucination, which is hard to tell apart from other…”
A Scoping Review of Artificial Intelligence for Precision Nutrition
Wu, X., Oniani, D., Shao, Z., Arciero, P. J., Sivarajkumar, S., Hilsman, J., Mohr, A. E., Ibe, S., Moharir, M., Li, L.-J., et al. (2025) · Advances in Nutrition · doi:10.1016/j.advnut.2025.100398 · Cited by 102
Dr ChatGPT tell me what I want to hear: How different prompts impact health answer correctness
Koopman, B., & Zuccon, G. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.928 · Cited by 73
Wang, R. E., & Demszky, D. (2023) · arXiv · doi:10.48550/arxiv.2306.03090 · Cited by 74
“However, their study only utilizes a single broad prompt to solicit feedback and they do not evaluate for common model issues like hallucination (Ji et al., 2023).”
BackgroundMethodBender, S. M. (2024) · Changing English · doi:10.1080/1358684x.2024.2309995 · Cited by 74
Dehallucinating Large Language Models Using Formal Methods Guided Iterative Prompting
Jha, S., Jha, S. K., Lincoln, P. D., Bastian, N. D., Velasquez, A., & Neema, S. K. (2023) · IEEE International Conference on Assured Autonomy (ICAA) · doi:10.1109/icaa58325.2023.00029 · Cited by 118
“However, these models are prone to hallucinations [3]–[6], that is, outputs that are factually incorrect or contextually inappropriate.”
BackgroundLanguage models for biological research: a primer
Simon, E. P., Swanson, K., & Zou, J. (2024) · Nature Methods · doi:10.1038/s41592-024-02354-y · Cited by 94
“Although natural language models are powerful tools for understanding the biological literature, one well-known limitation is their tendency to ‘hallucinate’ 11 , or generate coherent-sounding text that contains factual errors.”
Abstractive text summarization: State of the art, challenges, and improvements
Shakil, H., Farooq, A., & Kalita, J. K. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128255 · Cited by 133
“Despite advances, many summarization models struggle to adequately represent the meaning of the source text [150].”
On the Risk of Misinformation Pollution with Large Language Models
Pan, Y., Pan, L., Chen, W., Nakov, P., Kan, M.-Y., & Wang, W. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.97 · Cited by 210
Irfan, B., Kuoppamäki, S., Hosseini, A., & Skantze, G. (2025) · Autonomous Robots · doi:10.1007/s10514-025-10190-y · Cited by 108
“Moreover, LLMs are still far from perfect, with significant limitations in their ability to generate coherent and factual responses in open-domain dialogue (Ji et al., 2023).”
Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
Ling, C., Zhao, X., Lu, J., Deng, C., Zheng, C., Wang, J., Chowdhury, T., Li, Y., Cui, H., Zhang, X., et al. (2026) · ACM Computing Surveys · doi:10.1145/3764579 · Cited by 141
“researchers [59]; (4) lack of precision in certain tasks such as arithmetic [37].”
Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
Wang, J., Sun, Q., Li, X., & Gao, M. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.271 · Cited by 70
InsightPilot: An LLM-Empowered Automated Data Exploration System
Ma, P., Ding, R., Wang, S., Han, S., & Zhang, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2023.emnlp-demo.31 · Cited by 69
Agriculture 5.0: Cutting-Edge Technologies, Trends, and Challenges
Fountas, S., Espejo-García, B., Kasimati, A., Gemtou, M., Panoutsopoulos, H., & Anastasiou, E. (2024) · IT Professional · doi:10.1109/mitp.2024.3358972 · Cited by 93
Perspectives of Generative AI in Chemistry Education Within the TPACK Framework
Feldman-Maggor, Y., Blonder, R., & Alexandron, G. (2024) · Journal of Science Education and Technology · doi:10.1007/s10956-024-10147-3 · Cited by 130
“This aligns with Ji et al. (2023) who explained that “hallucinations” refer to a phenomenon where the model generates outputs that seem reasonable or convincing but are incorrect or not real (Ji et al., 2023).”
GLAT: The generative AI literacy assessment test
Jin, Y., Martinez-Maldonado, R., Gašević, D., & Yan, L. (2025) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2025.100436 · Cited by 76
Linking artificial intelligence facilitated academic misconduct to existing prevention frameworks
Birks, D., & Clare, J. (2023) · International Journal for Educational Integrity · doi:10.1007/s40979-023-00142-3 · Cited by 69
“LLMs potentially offer a step-change in natural language understanding and machine-human communication and can generate very plausible (though not always correct, e.g., Ji et al. 2023) responses to natural language prompts provided by a user.”
BackgroundContrastive Learning Reduces Hallucination in Conversations
Sun, W., Shi, Z., Gao, S., Ren, P., De Rijke, M., & Ren, Z. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26596 · Cited by 69
A Practical Survey on Zero-shot Prompt Design for In-context Learning
Columbia University, N. Y. C., & Li, Y. (2023) · Proceedings of the Conference Recent Advances in Natural Language Processing - Large Language Models for Natural Language Processings · doi:10.26615/978-954-452-092-2_069 · Cited by 68
Generative Artificial Intelligence in Finance: Risk Considerations
Shabsigh, G., & Boukherouaa, E. B. (2023) · Fintech Notes · doi:10.5089/9798400251092.063 · Cited by 117
HILL: A Hallucination Identifier for Large Language Models
Leiser, F., Eckhardt, S., Leuthe, V., Knaeble, M., Mädche, A., Schwabe, G., & Sunyaev, A. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642428 · Cited by 68
Wang, Y., Luo, H., & Fang, W. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103246 · Cited by 92
Zhang, E. Y., Cheok, A. D., Pan, Z., Cai, J., & Yan, Y. (2023) · Sci · doi:10.3390/sci5040046 · Cited by 106
“Ji et al. conducted a comprehensive survey of the issue of hallucination in natural language generation (NLG) [87].”
BackgroundXu, T., Liu, Y., Jin, Y., Qu, Y., Bai, J., Zhang, W., & Zhou, Y. (2025) · British Journal of Educational Technology · doi:10.1111/bjet.13530 · Cited by 67
Wang, Y., Pan, Y., Su, Z., Deng, Y., Zhao, Q., Du, L., Luan, T. H., Kang, J., & Niyato, D. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3576176 · Cited by 68
“For LLMs, source-reference divergence occurs due to heuristic data collection, implying that the selected sources may lack sufficient or accurate information for content generation [191].”
Ethical Challenges in the Development of Virtual Assistants Powered by Large Language Models
Piñeiro-Martín, A., García-Mateo, C., Docío-Fernández, L., & López-Pérez, M. D. C. (2023) · Electronics · doi:10.3390/electronics12143170 · Cited by 64
“Hallucinations are a well-known effect on the responses of Natural Language Generation (NLG) models and LLMs [28].”
BackgroundScaria, N., Chenna, S. D., & Subramani, D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-64299-9_12 · Cited by 147
“Although LLMs excel in various downstream tasks, they produce errors and inconsistencies [8], which can compromise the quality of the questions generated.”
BackgroundGenerative AIPreprint
Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4443189 · Cited by 65
Coşkun, B. N., Yağız, B., Ocakoğlu, G., Dalkılıç, E., & Pehlivan, Y. (2023) · Rheumatology International · doi:10.1007/s00296-023-05473-5 · Cited by 73
“It essentially 'imagines' or 'hallucinates' information, creating outputs that may seem plausible but are fundamentally incorrect [27].”
Gao, R., Lin, Y., Zhao, N., & Cai, Z. G. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-03363-0 · Cited by 134
“Such deviations, often referred to as “ hallucinations ” (Ji et al., 2023), have been a major point of criticism.”
Using generative ai as a simulation to support higher-order thinking
Borge, M., Smith, B. K., & Aldemir, T. (2024) · International Journal of Computer-Supported Collaborative Learning · doi:10.1007/s11412-024-09437-0 · Cited by 107
Research Directions in Software Supply Chain Security
Williams, L. A., Benedetti, G., Hamer, S., Paramitha, R., Rahman, I., Tamanna, M., Tystahl, G., Zahan, N., Morrison, P. J., Acar, Y., et al. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3714464 · Cited by 163
AIGC-empowered smart manufacturing: Prospects and challenges
Leng, J., Zheng, K., Li, R. C., Chen, C., Wang, B., Liu, Q., Chen, X., & Shen, W. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103076 · Cited by 84
Guerreiro, N. M., Voita, E., & Martins, A. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.75 · Cited by 63
The alignment problem from a deep learning perspective
Ngo, R., Chan, L., & Mindermann, S. (2022) · arXiv · doi:10.48550/arxiv.2209.00626 · Cited by 68
“However, this will become signifi-cantly more difficult as policies develop situational awareness , as described below.”
BackgroundRetrieving Supporting Evidence for Generative Question Answering
Huo, S., Arabzadeh, N., & Clarke, C. L. A. (2023) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3624918.3625336 · Cited by 107
“However, despite the excitement created by these improvements, the LLMs may confidently and convincingly generate hallucinated results [3, 17].”
BackgroundNatural Language Processing: Chances and Challenges in Dentistry
Büttner, M., Leser, U., Schneider, L., & Schwendicke, F. (2023) · Journal of Dentistry · doi:10.1016/j.jdent.2023.104796 · Cited by 75
Irfan, B., Kuoppamäki, S., & Skantze, G. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1363713 · Cited by 98
The effect of trust on user adoption of AI-generated content
Zhou, T., & Lu, H. (2024) · The Electronic Library · doi:10.1108/el-08-2024-0244 · Cited by 88
Liu, Y., Chen, S., Cheng, H., Yu, M., Ran, X., Mo, A., Tang, Y., & Huang, Y. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642698 · Cited by 61
“Given that LLMs are known to have problems with hallucination and lack of factual accuracy [26], creating high-quality RQs requires inputs from human researchers for their unique backgrounds and expertise.”
BackgroundHow artificial intelligence could transform emergency care
Kachman, M. M., Brennan, I., Oskvarek, J. J., Waseem, T. C., & Pines, J. M. (2024) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2024.04.024 · Cited by 85
Han, S., Wang, M., Zhang, J., Li, D., & Duan, J. (2024) · Electronics · doi:10.3390/electronics13245040 · Cited by 105
Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond
Xu, F., Lin, Q., Han, J., Zhao, T., Liu, J., & Cambria, E. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3536008 · Cited by 242
Has AlphaFold 3 achieved success for RNA?
Bernard, C., Postic, G., Ghannay, S., & Tahi, F. (2025) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798325000592 · Cited by 61
The Chatbots’ Challenge to Education: Disruption or Destruction?
Birenbaum, M. (2023) · Education Sciences · doi:10.3390/educsci13070711 · Cited by 61
Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity
Wang, C., Liu, X., Yue, Y., Tang, X., Zhang, T., Jiayang, C., Yao, Y., Gao, W., Hu, X., Qi, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.07521 · Cited by 61
Farhat, F., Chaudhry, B. M., Nadeem, M., Sohail, S. S., & Madsen, D. Ø. (2024) · JMIR Medical Education · doi:10.2196/51523 · Cited by 61
“It has been observed that LLMs, despite their impressive performance, can sometimes generate text that includes fabricated or incorrect information [13,23].”
BackgroundLarge language models in psychiatry: Opportunities and challenges
Volkmer, S., Meyer-Lindenberg, A., & Schwarz, E. (2024) · Psychiatry Research · doi:10.1016/j.psychres.2024.116026 · Cited by 59
Foundation models and intelligent decision-making: Progress, challenges, and perspectives
Huang, J., Xu, Y., Wang, Q., Wang, Q., Liang, X., Wang, F., Zhang, Z., Wei, W., Zhang, B., Huang, L., et al. (2025) · The Innovation · doi:10.1016/j.xinn.2025.100948 · Cited by 192
Self-citationArtificial Hallucinations by Google Bard: Think Before You Leap
Kumar, M., Mani, U. A., Tripathi, P., Saalim, M., & Roy, S. (2023) · Cureus · doi:10.7759/cureus.43313 · Cited by 59
“This instance of deliberate fabrication of information has been previously seen with ChatGPT and has been labelled "artificial hallucinations" [3-5].”
MethodGraph Neural Prompting with Large Language Models
Tian, Y., Song, H., Wang, Z., Wang, H., Hu, Z., Wang, F., Chawla, N. V., & Xu, P. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29875 · Cited by 197
QA-RAG: Exploring LLM Reliance on External Knowledge
Mansurova, A., Mansurova, A., & Nugumanova, A. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8090115 · Cited by 91
Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis
Bahr, L., Wehner, C., Wewerka, J., Bittencourt, J., Schmid, U., & Daub, R. (2025) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2025.100807 · Cited by 154
“Furthermore, LLMs tend to hallucinate, leading to misin-formation and making them unreliable in tasks where accurate knowledge recall is crucial [32, 33].”
Castellanos, A., Jiang, H., Gomes, P. J., VanderMeer, D. E., & Castillo, A. (2025) · JMIR AI · doi:10.2196/64447 · Cited by 74
“[16,17] Overfitting LLMs can sometimes focus too much on common or popular topics, missing out on niche or less frequently discussed topics.”
Epistemic Injustice in Generative AI
Kay, J., Kasirzadeh, A., & Mohamed, S. (2024) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1609/aies.v7i1.31671 · Cited by 76
Hadid, A., Chakraborty, T., & Busby, D. (2024) · Expert Systems · doi:10.1111/exsy.13654 · Cited by 91
Jacobsen, L. J., & Weber, K. E. (2025) · AI · doi:10.3390/ai6020035 · Cited by 58
“In our study, we focused on the comparison between LLMs, novices, and experts; however, we did not analyze intermediate skill levels or other feedback modalities (e.g., hybrid human–AI approaches).”
Kim, S. S. Y., Vaughan, J. W., Liao, Q. V., Lombrozo, T., & Russakovsky, O. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714020 · Cited by 58
Jacobsen, L. J., & Weber, K. E. (2023) · doi:10.31219/osf.io/cr257 · Cited by 57
Construction contract risk identification based on knowledge-augmented language models
Wong, S., Zheng, C., Su, X., & Tang, Y. (2024) · Computers in Industry · doi:10.1016/j.compind.2024.104082 · Cited by 100
The Illusion of Artificial Inclusion
Agnew, W., Bergman, A. S., Chien, J., Díaz, M., El-Sayed, S., Pittman, J., Mohamed, S., & McKee, K. R. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642703 · Cited by 58
Cambria, E., Zhang, X., Mao, R., Chen, M., & Kwok, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-76827-9_11 · Cited by 97
“This poses several risks [8], including ‘hallucination’ [26], which can lead to several ChatGPT failures, including reasoning, factual errors, math, coding, and bias [9].”
BackgroundPergantis, P., Bamicha, V., Skianis, C., & Drigas, A. S. (2025) · Brain Sciences · doi:10.3390/brainsci15010047 · Cited by 148
“The literature describes the erroneous results of AI chatbots as hallucinations or AI artifacts attributed to a misalignment between user expectations and the capabilities of the chatbot AI [63,64].”
A survey on retrieval-augmentation generation (RAG) models for healthcare applications
El-Enen, M. A. A., Saad, S., & Nazmy, T. M. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11666-9 · Cited by 121
Generative Ai in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity
Novelli, C., Casolari, F., Hacker, P., Spedicato, G., & Floridi, L. (2024) · doi:10.2139/ssrn.4821952 · Cited by 57
Faithful AI in Medicine: A Systematic Review with Large Language Models and Beyond
Xie, Q., Schenck, E. J., Yang, H. S., Chen, Y., Peng, Y., & Wang, F. (2023) · doi:10.21203/rs.3.rs-3661764/v1 · Cited by 57
“In the context of AI or NLP, faithful AI means the algorithm can produce contents that are factually correct, namely staying faithful to facts 17,20 .”
BackgroundMethodCRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Gou, Z., Shao, Z., Gong, Y., Shen, Y., Yang, Y., Duan, N., & Chen, W. (2023) · arXiv · doi:10.48550/arxiv.2305.11738 · Cited by 561
“, 2021) of language models for different downstream tasks (Ji et al., 2023), including abstractive summarization (Maynez et al.”
BackgroundHuang, R. S., Lu, K. J. Q., Meaney, C., Kemppainen, J., Punnett, A., & Leung, F.-H. (2023) · JMIR Medical Education · doi:10.2196/50514 · Cited by 56
Characterizing Manipulation from AI Systems
Carroll, M., Chan, A., Ashton, H., & Krueger, D. (2023) · Equity and Access in Algorithms, Mechanisms, and Optimization · doi:10.1145/3617694.3623226 · Cited by 60
“AI systems have documented problems with truthfulness [55, 86, 104].”
BackgroundSeeking empathy or suggesting a solution? Effects of chatbot messages on service failure recovery
Haupt, M., Rozumowski, A., Freidank, J., & Haas, A. (2023) · Electronic Markets · doi:10.1007/s12525-023-00673-0 · Cited by 57
“Thus, instead of acknowledging failure, ChatGPT often “hallucinates,” meaning that this kind of chat tools produce information that may be nonsen-sical, untrue, or inconsistent with the content of the source input (Dwivedi et al., 2023; Ji et al., 2023).”
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.




