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 101–200 of 4,844
Uncovering new families and folds in the natural protein universe
Durairaj, J., Waterhouse, A. M., Mets, T., Brodiazhenko, T., Abdullah, M., Studer, G., Tauriello, G., Akdel, M., Andreeva, A., Bateman, A., et al. (2023) · Nature · doi:10.1038/s41586-023-06622-3 · Cited by 152
“Given that language models have the tendency to ‘hallucinate’ predictions when faced with an unknown 23 , we propose that such an approach would generate a wide diversity of predicted names for completely new protein families.”
BackgroundMed-HALT: Medical Domain Hallucination Test for Large Language Models
Pal, A., Umapathi, L. K., & Sankarasubbu, M. (2023) · Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL) · doi:10.18653/v1/2023.conll-1.21 · Cited by 152
Med-HALT: Medical Domain Hallucination Test for Large Language Models
Pal, A., Umapathi, L. K., & Sankarasubbu, M. (2023) · arXiv · doi:10.48550/arxiv.2307.15343 · Cited by 152
Holderried, F., Stegemann-Philipps, C., Herrmann-Werner, A., Festl-Wietek, T., Holderried, M., Eickhoff, C., & Mahling, M. (2024) · JMIR Medical Education · doi:10.2196/59213 · Cited by 152
“…that GPT-4, given its capabilities in medical knowledge [24-26] and reasoning [13], can accurately assess students’ performance in history taking despite potential limitations such as logical errors [27] and AI’s propensity to generate nonsensical content, known as “hallucinations” [28].”
Retrieval-augmented generation for educational application: A systematic survey
Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., & Wang, F. L. (2025) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2025.100417 · Cited by 151
A Survey on the Memory Mechanism of Large Language Model based Agents
Zhang, Z., Bo, X., Ma, C., Li, R., Chen, X., Dai, Q., Zhu, J., Dong, Z., & Wen, J.-R. (2024) · arXiv · doi:10.48550/arxiv.2404.13501 · Cited by 149
Beware of botshit: How to manage the epistemic risks of generative chatbots
Hannigan, T. R., McCarthy, I. P., & Spicer, A. (2024) · Business Horizons · doi:10.1016/j.bushor.2024.03.001 · Cited by 224
Enhancing Static Analysis for Practical Bug Detection: An LLM-Integrated Approach
Li, H., Yu, H., Zhai, Y., & Qian, Z. (2024) · Proceedings of the ACM on Programming Languages · doi:10.1145/3649828 · Cited by 324
“Additionally, their inherent randomness might lead to inconsistent analyses, and their limited context windows might restrict the depth of their evaluations [Ji et al. 2023].”
BackgroundA Culturally Sensitive Test to Evaluate Nuanced GPT Hallucination
McIntosh, T. R., Liu, T., Susnjak, T., Watters, P., Ng, A., & Halgamuge, M. N. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3332837 · Cited by 145
Bewersdorff, A., Hartmann, C., Hornberger, M., Seßler, K., Bannert, M., Kasneci, E., Kasneci, G., Zhai, X., & Nerdel, C. (2025) · Learning and Individual Differences · doi:10.1016/j.lindif.2024.102601 · Cited by 148
“Incorporating human feedback through the training of reward models and applying reinforcement learning in the fine-tuning step [Lee et al. 2023b; Ouyang et al. 2022] has significantly enhanced the generation of human-like language that is aligned with social norms and goals and has led to the…”
Anh-Hoang, D., Tran, V., & Nguyen, L.-M. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1622292 · Cited by 146
“High-confidence hallucinations—those that appear fluent and plausible but are factually incorrect—are particularly dangerous and difficult to detect automatically (Kadavath et al., 2022; Ji et al., 2023).”
InfluentialThe Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies
Swanson, K., Wu, W., Bulaong, N. L., Pak, J. E., & Zou, J. (2025) · Nature · doi:10.1038/s41586-025-09442-9 · Cited by 169
“The current generation of LLMs is also known to sometimes provide incorrect or misleading answers (often termed hallucinations 50 ).”
Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review
Zhang, W., & Zhang, J. (2025) · Mathematics · doi:10.3390/math13050856 · Cited by 145
Van Bulck, L., & Moons, P. (2024) · European Journal of Cardiovascular Nursing · doi:10.1093/eurjcn/zvad038 · Cited by 143
Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models
Xi, Y., Liu, W., Lin, J., Cai, X., Zhu, H., Zhu, J., Chen, B., Tang, R., Zhang, W., & Yu, Y. (2024) · 18th ACM Conference on Recommender Systems · doi:10.1145/3640457.3688104 · Cited by 151
“Moreover, the knowledge generated by LLMs can sometimes be unreliable or misleading due to the hallucination problem [21].”
BackgroundWhen Human-AI Interactions Become Parasocial: Agency and Anthropomorphism in Affective Design
Maeda, T., & Quan-Haase, A. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658956 · Cited by 144
Oniani, D., Hilsman, J., Peng, Y., Poropatich, R. K., Pamplin, J. C., Legault, G. L., & Wang, Y. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00965-x · Cited by 143
“The proximity of generative AI to patient well-being necessitates standards for reliability to minimize potential errors that could lead to accidents 43 .”
BackgroundInfluentialKuang, W., Qian, B., Li, Z., Chen, D., Gao, D., Pan, X., Xie, Y., Li, Y., Ding, B., & Zhou, J. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671573 · Cited by 142
“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 (Ji et al., 2023).”
Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models
Lin, Z., Guan, S., Zhang, W., Zhang, H., Li, Y., & Zhang, H. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10896-y · Cited by 141
Performance of Generative Large Language Models on Ophthalmology Board–Style Questions
Cai, L. Z., Shaheen, A., Jin, A., Fukui, R., Yi, J. S., Yannuzzi, N., & Alabiad, C. (2023) · American Journal of Ophthalmology · doi:10.1016/j.ajo.2023.05.024 · Cited by 139
ChatClimate: Grounding conversational AI in climate science
Vaghefi, S. A., Stammbach, D., Muccione, V., Bingler, J., Ni, J., Kraus, M., Allen, S., Colesanti-Senni, C., Wekhof, T., Schimanski, T., et al. (2023) · Communications Earth & Environment · doi:10.1038/s43247-023-01084-x · Cited by 135
Self-citationKim, S. S. Y., Liao, Q. V., Vorvoreanu, M., Ballard, S., & Vaughan, J. W. (2024) · The 2024 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3630106.3658941 · Cited by 147
Bridging the Gulf of Envisioning: Cognitive Challenges in Prompt Based Interactions with LLMs
Subramonyam, H., Pea, R., Pondoc, C., Agrawala, M., & Seifert, C. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642754 · Cited by 162
Biomedical knowledge graph-optimized prompt generation for large language models
Soman, K., Rose, P. W., Morris, J. H., Akbas, R. E., Smith, B., Peetoom, B., Villouta-Reyes, C., Cerono, G., Shi, Y., Rizk-Jackson, A., et al. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae560 · Cited by 135
“Nevertheless, the “implicit representation” of knowledge in LLM has also been shown to generate non-factual information despite linguistically coherent answers (i.e. “hallucination”) as a response to the input prompt (Maynez et al. 2020, Raunak et al. 2021, Ji et al. 2023).”
BackgroundHarms from Increasingly Agentic Algorithmic Systems
Chan, A., Salganik, R., Markelius, A., Pang, C., Rajkumar, N., Krasheninnikov, D., Langosco, L., He, Z., Duan, Y., Carroll, M., et al. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594033 · Cited by 149
“models, recent studies [Ji et al. 2022; Valmeekam et al. 2022] have shown that large language models can perform poorly on planning and reasoning tasks, and such systems are prone to hallucinate unintended text, which fails to meet users’ intents on many real-world scenarios.”
BackgroundResultAssessing the utility of ChatGPT throughout the entire clinical workflow
Rao, A., Pang, M., Kim, J., Kamineni, M., Lie, W., Prasad, A. K., Landman, A., Dreyer, K. J., & Succi, M. D. (2023) · doi:10.1101/2023.02.21.23285886 · Cited by 134
Early warning of complex climate risk with integrated artificial intelligence
Reichstein, M., Benson, V., Blunk, J., Camps‐Valls, G., Creutzig, F., Fearnley, C. J., Han, B., Kornhuber, K., Rahaman, N., Schölkopf, B., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-57640-w · Cited by 242
Retrieval-Augmented Generation (RAG) Chatbots for Education: A Survey of Applications
Swacha, J., & Gracel, M. (2025) · Applied Sciences · doi:10.3390/app15084234 · Cited by 249
Storey, V. C., Yue, W. T., Zhao, J. L., & Lukyanenko, R. (2025) · Information Systems Frontiers · doi:10.1007/s10796-025-10581-7 · Cited by 294
“The "hallucination" problem for large language models (Ji et al., 2023) means that GenAI has a tendency to generate nonsensical outputs based on specified inputs.”
Zheng, S., Pan, K., Liu, J., & Chen, Y. (2024) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2024.110382 · Cited by 127
Best Practices for Using AI Tools as an Author, Peer Reviewer, or Editor
Leung, T. I., de Azevedo Cardoso, T., Mavragani, A., & Eysenbach, G. (2023) · Journal of Medical Internet Research · doi:10.2196/51584 · Cited by 127
Teaching Small Language Models to Reason
Magister, L. C., Mallinson, J., Adamek, J., Malmi, E., & Severyn, A. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/2023.acl-short.151 · Cited by 127
Huang, Q., Dong, X., Zhang, P., Wang, B., He, C., Wang, J., Lin, D., Zhang, W., & Yu, N. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01274 · Cited by 136
“The hallucination [21, 43] refers to the generation of text that is either irrelevant, factually incorrect, or nonsensical in the given context, which is quite severe in current large foundation models.”
Generative AI for visualization: State of the art and future directions
Ye, Y., Hao, J., Hou, Y., Wang, Z., Xiao, S., Luo, Y., & Zeng, W. (2024) · Visual Informatics · doi:10.1016/j.visinf.2024.04.003 · Cited by 219
Truhn, D., Loeffler, C. M., Müller‐Franzes, G., Nebelung, S., Hewitt, K. J., Brandner, S., Bressem, K. K., Foersch, S., & Kather, J. N. (2024) · The Journal of Pathology · doi:10.1002/path.6232 · Cited by 124
“It should also be noted that generative models can ‘ hallucinate ’ fi ndings [5,16].”
BackgroundGenerative AI in EU law: Liability, privacy, intellectual property, and cybersecurity
Novelli, C., Casolari, F., Hacker, P., Spedicato, G., & Floridi, L. (2024) · Computer Law & Security Review · doi:10.1016/j.clsr.2024.106066 · Cited by 124
Hallucinations in Large Multilingual Translation Models
Guerreiro, N. M., Alves, D. M., Waldendorf, J., Haddow, B., Birch, A., Colombo, P., & Martins, A. F. T. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00615 · Cited by 124
Hallucinations in Large Multilingual Translation Models
Guerreiro, N. M., Alves, D., Waldendorf, J., Haddow, B., Birch, A., Colombo, P., & Martins, A. F. T. (2023) · arXiv · doi:10.48550/arxiv.2303.16104 · Cited by 124
The limitations and ethical considerations of ChatGPT
Hua, S., Jin, S., & Jiang, S. (2024) · Data Intelligence · doi:10.1162/dint_a_00243 · Cited by 120
Kraljevic, Z., Bean, D., Shek, A., Bendayan, R., Hemingway, H., Yeung, J. A., Deng, A., Balston, A., Ross, J., Idowu, E., et al. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(24)00025-6 · Cited by 169
“Finally, hallucinations are also well described in transformerbased generative models, 24,25 including the recent ChatGPT, so such relevancy and mitigation systems would need to be built before the model would be suitable for clinical decision support.”
Li, H., Moon, J. T., Iyer, D., Balthazar, P., Krupinski, E. A., Bercu, Z. L., Newsome, J. M., Banerjee, I., Gichoya, J. W., & Trivedi, H. M. (2023) · Clinical Imaging · doi:10.1016/j.clinimag.2023.06.008 · Cited by 118
“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters
Wan, Y., Pu, G., Sun, J., Garimella, A., Chang, K.-W., & Peng, N. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.243 · Cited by 136
Generative Artificial Intelligence Through ChatGPT and Other Large Language Models in Ophthalmology
Tan, T. F., Thirunavukarasu, A. J., Campbell, J. P., Keane, P. A., Pasquale, L. R., Abramoff, M. D., Kalpathy-Cramer, J., Lum, F., Kim, J. E., Baxter, S. L., et al. (2023) · Ophthalmology Science · doi:10.1016/j.xops.2023.100394 · Cited by 116
“72 Therefore, it is important to build LLM applications that acknowledge doubt and uncertainty rather than outputting unmitigated erroneous responses.”
BackgroundLarge language models: a survey of their development, capabilities, and applications
Yadagiri, A., & Pakray, P. (2024) · Knowledge and Information Systems · doi:10.1007/s10115-024-02310-4 · Cited by 218
Using ChatGPT for human–computer interaction research: a primer
Tabone, W., & de Winter, J. (2023) · Royal Society Open Science · doi:10.1098/rsos.231053 · Cited by 116
“valid) or a hallucination (a known issue with large language models; [57]) requires further consideration.”
BackgroundTowards multimodal foundation models in molecular cell biology
Cui, H., Tejada-Lapuerta, A., Brbić, M., Sáez-Rodríguez, J., Cristea, S., Goodarzi, H., Lotfollahi, M., Theis, F. J., & Wang, B. (2025) · Nature · doi:10.1038/s41586-025-08710-y · Cited by 186
“Hallucination, a substantial challenge and potential limitation for MFMs, originally refers to the generation of plausible but factually incorrect or nonsensical outputs 116,117 .”
Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models
Yang, K.-C., & Menczer, F. (2023) · arXiv · doi:10.48550/arxiv.2304.00228 · Cited by 115
Addressing 6 challenges in generative AI for digital health: A scoping review
Templin, T., Perez, M. W., Sylvia, S., Leek, J. T., & Sinnott-Armstrong, N. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000503 · Cited by 139
“Generative AI can exhibit biases [9,10], compromise data privacy [11,12], misinterpret prompts[13,14], and produce hallucinations [15].”
BackgroundLong, S., Tan, J., Mao, B., Tang, F., Li, Y., Zhao, M., & Kato, N. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3526606 · Cited by 166
MedChatZH: A tuning LLM for traditional Chinese medicine consultations
Tan, Y., Zhang, Z., Li, M., Pan, F., Duan, H., Huang, Z., Deng, H., Yu, Z., Yang, C., Shen, G., et al. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108290 · Cited by 141
Salah, M., Al Halbusi, H., & Abdelfattah, F. (2023) · Computers in Human Behavior: Artificial Humans · doi:10.1016/j.chbah.2023.100006 · Cited by 112
MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling
Kim, T., Bae, S., Kim, H. A., Lee, S.-W., Hong, H., Yang, C., & Kim, Y.-H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642937 · Cited by 112
Fine-tuning large language models for chemical text mining
Zhang, W., Wang, Q., Kong, X., Xiong, J., Ni, S., Cao, D., Niu, B., Chen, M., Li, Y., Zhang, R., et al. (2024) · Chemical Science · doi:10.1039/d4sc00924j · Cited by 113
“12,13 Moreover, objectively evaluating the results of open-ended questions remains a signi cant challenge.”
Artificial hallucination: GPT on LSD?
Beutel, G., Geerits, E., & Kielstein, J. T. (2023) · Critical Care · doi:10.1186/s13054-023-04425-6 · Cited by 111
“However, it should be noted that artificial hallucination is not a new phenomenon as discussed in [6].”
BackgroundBalas, M., & Ing, E. B. (2023) · JFO Open Ophthalmology · doi:10.1016/j.jfop.2023.100005 · Cited by 110
Knowledge Injection to Counter Large Language Model (LLM) Hallucination
Martino, A., Iannelli, M., & Truong, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43458-7_34 · Cited by 246
“One limitation of Large Language Model (LLM) content generation is hallucination, or false assertions in the generated text [2].”
BackgroundHow understanding large language models can inform the use of ChatGPT in physics education
Polverini, G., & Gregorcic, B. (2024) · European Journal of Physics · doi:10.1088/1361-6404/ad1420 · Cited by 107
“Humans, including researchers, often explicitly or implicitly attribute to LLMs abilities like “thinking”, “reasoning”, “understanding”, and “knowing” [30] and, as we mentioned before, “hallucinating” 7 [31].”
BackgroundMatsumoto, N., Moran, J., Choi, H., Hernandez, M. E., Venkatesan, M., Wang, P., & Moore, J. H. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae353 · Cited by 108
“While LLMs can produce fluent and coherent texts, without proper vetting, they may lack factual consistency and may introduce irrelevant or false information that is not supported by evidence (Ji et al. 2023).”
BackgroundChen, C., Zhao, K., Leng, J., Liu, C., Fan, J., & Zheng, P. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.102982 · Cited by 137
Recent Advances in Large Language Models for Healthcare
Nassiri, K., & Akhloufi, M. A. (2024) · BioMedInformatics · doi:10.3390/biomedinformatics4020062 · Cited by 135
“One of the major challenges encountered in medical QA systems is the problem of hallucinations leading to incorrect answers [173].”
BackgroundHadi, M. U., tashi, Q. A., Qureshi, R., Shah, A., muneer, A., Irfan, M., Zafar, A., Shaikh, M. B., Akhtar, N., Wu, J., et al. (2023) · doi:10.36227/techrxiv.23589741.v4 · Cited by 103
A Mathematical Investigation of Hallucination and Creativity in GPT Models
Lee, M. (2023) · Mathematics · doi:10.3390/math11102320 · Cited by 105
Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence
McIntosh, T. R., Susnjak, T., Arachchilage, N., Liu, T., Watters, P., & Halgamuge, M. N. (2024) · arXiv · doi:10.48550/arxiv.2402.09880 · Cited by 104
Generative AI: Opportunities, challenges, and research directions for supply chain resilience
Boone, T., Fahimnia, B., Ganeshan, R., Herold, D. M., & Sanders, N. R. (2025) · Transportation Research Part E Logistics and Transportation Review · doi:10.1016/j.tre.2025.104135 · Cited by 144
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102
“Hallucination reduction is a persistent challenge in LLMs, characterized by the generation of confident but factually incorrect information [36].”
BackgroundInfluentialWang, P. Q. (2024) · Current Issues in Tourism · doi:10.1080/13683500.2023.2300030 · Cited by 150
“Ji et al. (2023) define hallucination as the generation of nonsen-sical or unfaithful content.”
Foundation Models: A New Paradigm for Artificial Intelligence
Schneider, J., Meske, C., & Kuss, P. (2024) · Business & Information Systems Engineering · doi:10.1007/s12599-024-00851-0 · Cited by 104
“Rapid fact-checking constitutes another important skill for efficient and responsible use, given the unresolved issue of hallucinations with AI applications based on large-scale foundation models (Ji et al. 2023).”
A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models
Zhang, H., Yu, P. S., & Zhang, J. (2025) · ACM Computing Surveys · doi:10.1145/3731445 · Cited by 327
LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
Zhang, Z., Wang, C., Wang, Y., Shi, E., Ma, Y., Zhong, W., Chen, J., Mao, M., & Zheng, Z. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3728894 · Cited by 314
“Specifically, RAG has successfully resolved approximately 8% of Project Context Conflicts and about 6% of Task Requirement Conflicts .”
InfluentialDeception abilities emerged in large language models
Hagendorff, T. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2317967121 · Cited by 100
Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence
McIntosh, T. R., Susnjak, T., Arachchilage, N., Liu, T., Xu, D., Watters, P., & Halgamuge, M. N. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3569516 · Cited by 104
“For example, if an LLM-generated benchmark unintentionally reinforces specific patterns or knowledge it was trained on, it may allow LLMs to perform well through pattern recognition rather than demonstrating genuine understanding or reasoning [56], [58].”
BackgroundTool learning with large language models: a survey
Qu, C., Dai, S., Wei, X., Cai, H., Wang, S., Yin, D., Xu, J., & Wen, J.-R. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-024-40678-2 · Cited by 99
“This inherent limitation frequently results in responses that are plausible yet factually incorrect or outdated (often referred to as hallucination) [14, 15], posing significant risks and misleading users.”
RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Model
Tsai, Y., Liu, M., & Ren, H. (2024) · Proceedings of the 61st ACM/IEEE Design Automation Conference · doi:10.1145/3649329.3657353 · Cited by 116
Lewandowski, M., Łukowicz, P., Świetlik, D., & Barańska-Rybak, W. (2024) · Clinical and Experimental Dermatology · doi:10.1093/ced/llad255 · Cited by 97
A comprehensive survey of large language models and multimodal large language models in medicine
Xiao, H., Zhou, F., Liu, X., Liu, T., Li, Z., Liu, X., & Huang, X. (2025) · Information Fusion · doi:10.1016/j.inffus.2024.102888 · Cited by 113
“Hallucinations refer to the generation of seemingly plausible yet unverified or incorrect information by LLMs and MLLMs [29, 30].”
Unifying Large Language Models and Knowledge Graphs: A RoadmapPreprint
Pan, S., Luo, L., Wang, Y., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.08302 · Cited by 97
“However, LLMs are often criticized for their hallucination issues [15], and lacking of interpretability.”
BackgroundInfluentialZhang, C., Liu, X., Ziska, K., Jeon, S., Yu, C.-L., & Xu, Y. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642647 · Cited by 96
Self-citationNakaura, T., Yoshida, N., Kobayashi, N., Shiraishi, K., Nagayama, Y., Uetani, H., Kidoh, M., Hokamura, M., Funama, Y., & Hirai, T. (2024) · Japanese Journal of Radiology · doi:10.1007/s11604-023-01487-y · Cited by 96
The ethics of using generative AI for qualitative data analysis
Davison, R. M., Chughtai, H., Nielsen, P., Marabelli, M., Iannacci, F., Offenbeek, V. M., Tarafdar, M., Trenz, M., Techatassanasoontorn, A. A., Andrade, A. D., et al. (2024) · Information Systems Journal · doi:10.1111/isj.12504 · Cited by 178
Herrmann-Werner, A., Festl-Wietek, T., Holderried, F., Herschbach, L., Griewatz, J., Masters, K., Zipfel, S., & Mahling, M. (2024) · Journal of Medical Internet Research · doi:10.2196/52113 · Cited by 96
“Mechanistically, language models such as GPT use likelihood maximization, generating text based on what most likely follows [16,34].”
Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
Chen, Y., Fu, Q., Yuan, Y., Wen, Z., Fan, G., Liu, D., Zhang, D., Li, Z., & Xiao, Y. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3614905 · Cited by 94
Park, K., & Yoon, H. Y. (2024) · Public Relations Review · doi:10.1016/j.pubrev.2024.102507 · Cited by 147
Park, J., Oh, K., Han, K., & Lee, Y. H. (2024) · Scientific Reports · doi:10.1038/s41598-024-63824-z · Cited by 94
LLMs Will Always Hallucinate, and We Need to Live with This
Banerjee, S., Agarwal, A., & Singla, S. (2025) · Lecture Notes in Networks and Systems · doi:10.1007/978-3-031-99965-9_39 · Cited by 93
Generative Pre-Trained Transformer (GPT) in Research: A Systematic Review on Data Augmentation
Sufi, F. K. (2024) · Information · doi:10.3390/info15020099 · Cited by 151
Integrating LLMs With ITS: Recent Advances, Potentials, Challenges, and Future Directions
Mahmud, D., Hajmohamed, H., Almentheri, S., Alqaydi, S., Aldhaheri, L., Khalil, R. A., & Saeed, N. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3528116 · Cited by 141
“Training LLMs from scratch can take weeks or months on high-performance hardware, and even after training, the models require substantial resources during inference, particularly in time-sensitive tasks like traffic management [217], [218].”
When Large Language Models Meet Vector Databases: A Survey
Jing, Z., Su, Y., & Han, Y. (2025) · 2025 Conference on Artificial Intelligence x Multimedia (AIxMM) · doi:10.1109/aixmm62960.2025.00008 · Cited by 93
“One major challenge is hallucinations in LLMs [20], which undermine the reliability of their outputs.”
BackgroundBarman, D., Guo, Z., & Conlan, O. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100545 · Cited by 92
Large language models in biomedicine and health: current research landscape and future directions
Lu, Z., Peng, Y., Cohen, T., Ghassemi, M., Weng, C., & Tian, S. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae202 · Cited by 92
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Casper, S., Davies, X., Shi, C., Gilbert, T. K., Scheurer, J., Rando, J., Freedman, R., Korbak, T., Lindner, D., Freire, P., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.15217 · Cited by 101
“A body of work on using language feedback for reward inference and shaping might lessen this challenge [Fu et al., 2019, Goyal et al., 2019, Sumers et al., 2021, Zhou and Small, 2021, Lin et al., 2022, Yu et al., 2023], but thus far, these techniques have not been applied to LLMs.”
BackgroundTriguero, I., Molina, D., Poyatos, J., Del Ser, J., & Herrera, F. (2024) · Information Fusion · doi:10.1016/j.inffus.2023.102135 · Cited by 90
Synthetic data in biomedicine via generative artificial intelligence
van Breugel, B., Liu, T., Oglic, D., & van der Schaar, M. (2024) · Nature Reviews Bioengineering · doi:10.1038/s44222-024-00245-7 · Cited by 109
“For example, users can generate data for different fairness notions, or use interactive simulators to create outcomes under dif ferent synthetic environments.”
Ntinopoulos, V., Biefer, H. R. C., Tudorache, I., Papadopoulos, N., Odavic, D., Risteski, P. S., Haeussler, A., & Dzemali, O. (2025) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2024-101139 · Cited by 132
Chervenak, J., Lieman, H., Blanco-Breindel, M., & Jindal, S. (2023) · Fertility and Sterility · doi:10.1016/j.fertnstert.2023.05.151 · Cited by 87
Mustapha, K. B. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.103066 · Cited by 118
Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
Renze, M., & Guven, E. (2024) · arXiv · doi:10.48550/arxiv.2405.06682 · Cited by 89
Careless Whisper: Speech-to-Text Hallucination Harms
Koenecke, A., Choi, A. S. G., Mei, K. X., Schellmann, H., & Sloane, M. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658996 · Cited by 89
Performance of ChatGPT in Diagnosis of Corneal Eye Diseases
Delsoz, M., Madadi, Y., Raja, H., Munir, W. M., Tamm, B., Mehravaran, S., Soleimani, M., Djalilian, A., & Yousefi, S. (2024) · Cornea · doi:10.1097/ico.0000000000003492 · Cited by 86
“33 Although our study is one of the fi rst investigations of ChatGPT capabilities in diagnosing corneal conditions, it has several limitations as well.”
BackgroundFramework for Adoption of Generative Artificial Intelligence (GenAI) in Education
Shailendra, S., Kadel, R., & Sharma, A. (2024) · IEEE Transactions on Education · doi:10.1109/te.2024.3432101 · Cited by 88
“This can occur due to various factors, such as noisy data, erroneous parametric knowledge, flawed attention mechanisms, or inadequate training strategies [18].”
BackgroundExploring the role of large language models in the scientific method: from hypothesis to discovery
Zhang, Y., Khan, S. A., Mahmud, A., Yang, H., Lavin, A., Levin, M. G., Frey, J. G., Dunnmon, J., Evans, J. A., Bundy, A., et al. (2025) · npj Artificial Intelligence · doi:10.1038/s44387-025-00019-5 · Cited by 247
“This is analogous to hallucination in human psychology, though, for LLMs, it manifests as unjusti fi ed responses or beliefs rather than perceptual hallucinations 148 .”
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.




