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 501–600 of 4,844
Lee, Y. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-13129-5 · Cited by 59
“Generative Artificial Intelligence (GAI), while exhibiting remarkable capabilities, is known to produce responses containing false or misleading information (Ji et al., 2023).”
Enhanced E-Commerce Personalization Through AI-Powered Content Generation Tools
Wasilewski, A., Chawla, Y., & Prałat, E. (2025) · IEEE Access · doi:10.1109/access.2025.3550956 · Cited by 45
“A particularly critical issue is the phenomenon of ‘‘artificial hallucination,’’ where AI systems generate inaccurate or misleading information [24].”
Zhao, Y., Yang, M., Lin, Y., Zhang, X., Shi, F., Wang, Z., Ding, J., & Ning, H. (2025) · Electronics · doi:10.3390/electronics14061197 · Cited by 64
Academic journals’ AI policies fail to curb the surge in AI-assisted academic writing
He, Y., & Bu, Y. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2526734123 · Cited by 85
“While enhancing research efficiency (14) and breaking down language barriers (15) to promote global knowledge sharing (16, 17), AI also raises concerns about hallucinations (18), potential ethical issues, and controversies over whether AI should be credited as an author (19).”
Sezgin, E., Jackson, D. I., Kocaballi, A. B., Bibart, M., Zupanec, S., Landier, W., Audino, A., Ranalli, M., & Skeens, M. (2025) · Cancer Medicine · doi:10.1002/cam4.70554 · Cited by 30
Song, Y., Cui, M., Wan, F., Yu, Z., & Jiang, J. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2025.2483858 · Cited by 30
“(Ji et al., 2023) The generated content that is nonsensical or unfaithful to the provided source content.”
InfluentialMeasuring and Modifying Factual Knowledge in Large Language Models
Pezeshkpour, P. (2023) · arXiv · doi:10.48550/arxiv.2306.06264 · Cited by 30
KOGI: A Seamless Integration of ChatGPT into Jupyter Environments for Programming Education
Kuramitsu, K., Obara, Y., Sato, M., & Obara, M. (2023) · ACM SIGPLAN International Symposium on SPLASH-E (SPLASH-E) · doi:10.1145/3622780.3623648 · Cited by 52
Yazaki, M., Maki, S., Furuya, T., Inoue, K., Nagai, K., Nagashima, Y., Maruyama, J., Toki, Y., Kitagawa, K., Iwata, S., et al. (2025) · Prehospital Emergency Care · doi:10.1080/10903127.2024.2374400 · Cited by 29
“In particular, in emergency medical situations requiring expertise and urgency, there are concerns about the reliability of AI judgments and the occurrence of hallucinations based on incorrect information (9,10).”
Patchview: LLM-powered Worldbuilding with Generative Dust and Magnet Visualization
Chung, J. J. Y., & Kreminski, M. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676352 · Cited by 57
Deception and manipulation in generative AI
Tarsney, C. J. (2025) · Philosophical Studies · doi:10.1007/s11098-024-02259-8 · Cited by 65
“They are notoriously subject to “hallucination”, confidently asserting entirely imaginary facts (Ji et al., 2023)—including, for instance, potentially slanderous falsehoods about real people (Poritz, 2023; Verma and Oremus, 2023).”
Large language models can better understand knowledge graphs than we thought
Dai, X., Hua, Y., Wu, T., Yang, S., Qiu, J., & Qi, G. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113060 · Cited by 64
Jin, Y., Yang, K., Yan, L., Echeverría, V., Zhao, L., Alfredo, R., Milesi, M. E., Fan, J. X., Li, X., Gašević, D., et al. (2025) · International Conference on Learning Analytics and Knowledge (LAK) · doi:10.1145/3706468.3706545 · Cited by 58
From Questions to Insightful Answers: Building an Informed Chatbot for University Resources
Neupane, S., Hossain, E., Keith, J., Tripathi, H., Ghiasi, F., Golilarz, N. A., Amirlatifi, A., Mittal, S., & Rahimi, S. (2024) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie61694.2024.10892994 · Cited by 69
“To address this, hybrid approaches like Retrieval Augmented Generation (RAG) have emerged [14], [17], [18].”
The Role of AI-Based Chatbots in Public Health Emergencies: A Narrative Review
Branda, F., Stella, M., Ceccarelli, C., Cabitza, F., Ceccarelli, G., Maruotti, A., Ciccozzi, M., & Scarpa, F. (2025) · Future Internet · doi:10.3390/fi17040145 · Cited by 51
“Further research is needed to develop evaluation metrics and real-time verification systems to ensure reliability in high-stakes domains [104].”
An outline of Prognostics and health management Large Model: Concepts, Paradigms, and challenges
Tao, L., Li, S., Liu, H., Huang, Q., Ma, L., Ning, G., Chen, Y., Wu, Y., Li, B., Zhang, W., et al. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112683 · Cited by 44
Wang, R., & Demszky, D. (2023) · Workshop on Innovative Use of NLP for Building Educational Applications · doi:10.18653/v1/2023.bea-1.53 · Cited by 72
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model
Hsu, I.-H., Xie, Z., Huang, K.-H., Natarajan, P., & Peng, N. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.615 · Cited by 73
Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
Dai, W., Liu, Z., Ji, Z., Su, D., & Fung, P. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.156 · Cited by 103
Self-citationAutomatic Evaluation of Attribution by Large Language Models
Yue, X., Wang, B., Chen, Z., Zhang, K., Su, Y., & Sun, H. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.307 · Cited by 32
Evidence-centered Assessment for Writing with Generative AI
Cheng, Y., Lyons, K., Chen, G., Gašević, D., & Swiecki, Z. (2024) · Proceedings of the 14th Learning Analytics and Knowledge Conference · doi:10.1145/3636555.3636866 · Cited by 29
“…to maintain a reality status; and (4) authors responding to argumentative writing prompts would have writing processes more characterised by knowledge transformation, integration, and resolution as they may have needed to align GAI outputs (which are known to include falsehoods [34]) with reality.”
BackgroundKoLA: Carefully Benchmarking World Knowledge of Large Language Models
Yu, J., Wang, X., Tu, S., Cao, S., Zhang-Li, D., Lv, X., Peng, H., Yao, Z., Zhang, X., Li, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.09296 · Cited by 29
“Furthermore, evaluating knowledge creation is particularly challenging as it involves distinguishing the correctly created knowledge and knowledge hallucinations (Ji et al., 2023).”
BackgroundLi, R., Wang, X., & Yu, H. Q. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.474 · Cited by 73
Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward
Yang, M., Zhu, M., Wang, Y., Chen, L., Zhao, Y., Wang, X. H., Han, B., Zheng, X., & Yin, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i8.28777 · Cited by 67
Ono, D., Dickson, D. W., & Koga, S. (2024) · Neuropathology and Applied Neurobiology · doi:10.1111/nan.12997 · Cited by 39
RadioRAG: Online Retrieval–Augmented Generation for Radiology Question Answering
Arasteh, S. T., Lotfinia, M., Bressem, K. K., Siepmann, R. M., Adams, L. C., Ferber, D., Kuhl, C. K., Kather, J. N., Nebelung, S., & Truhn, D. (2025) · Radiology Artificial Intelligence · doi:10.1148/ryai.240476 · Cited by 67
“However, the use of LLMs in radiology comes with challenges, most prominently the risk of generating inaccurate information and perpetuating biases 10 – 12 .”
Conformal Prediction for Natural Language Processing: A Survey
Campos, M., Farinhas, A., Zerva, C., Figueiredo, M. A. T., & Martins, A. F. T. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00715 · Cited by 126
How do judges use large language models? Evidence from Shenzhen
Liu, J. Z., & Li, X. (2024) · The Journal of Legal Analysis · doi:10.1093/jla/laae009 · Cited by 54
TDAG: A multi-agent framework based on dynamic Task Decomposition and Agent Generation
Wang, Y., Wu, Z., Yao, J., & Su, J. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107200 · Cited by 103
Artificial Intelligence in Ecology: A Commentary on a Chatbot's Perspective
Haghighi, S. R., Saqalaksari, M. P., & Johnson, S. N. (2023) · Bulletin of the Ecological Society of America · doi:10.1002/bes2.2097 · Cited by 47
Artificial intelligence—friend or foe in fake news campaigns
Węcel, K., Sawiński, M., Stróżyna, M., Lewoniewski, W., Księżniak, E., Stolarski, P., & Abramowicz, W. (2023) · Economics and Business Review · doi:10.18559/ebr.2023.2.736 · Cited by 28
“At the moment AI is notorious for producing texts not consistent with real‐ ity and with confused facts, the phenomenon known as hallucination (Ji et al., 2022).”
BackgroundDale, D. C., Voita, E., Barrault, L., & Costa‐jussà, M. R. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.3 · Cited by 121
Sheth, S., Baker, H. P., Prescher, H., & Strelzow, J. (2024) · Journal of the American Academy of Orthopaedic Surgeons · doi:10.5435/jaaos-d-23-00787 · Cited by 34
Wang, R., & Demszky, D. (2023) · EdArXiv (OSF Preprints) · doi:10.35542/osf.io/5vrby · Cited by 75
Kumamoto, T., Yoshida, Y., & Fujima, H. (2023) · Research Square · doi:10.21203/rs.3.rs-3719038/v1 · Cited by 35
The Uneven Impact of Generative AI on Entrepreneurial PerformancePreprint
Otis, N. G., Clarke, R. P., Delecourt, S., Holtz, D., & Koning, R. M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4671369 · Cited by 110
Knowledge Graph-Enhanced Large Language Models via Path Selection
Liu, H., Wang, S., Zhu, Y., Dong, Y., & Li, J. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.376 · Cited by 28
Dolmestch, R. N. (2023) · Derecho PUCP · doi:10.18800/derechopucp.202302.007 · Cited by 87
Wang, L., He, J., Li, S., Liu, N., & Lim, E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-53302-0_3 · Cited by 106
LLM-based Robot Task Planning with Exceptional Handling for General Purpose Service Robots
Wang, R., Yang, Z., Zhao, Z., Tong, X., Hong, Z., & Qian, K. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10661966 · Cited by 60
“1: The work process of our prompt scheme. nations [9, 13], resulting in content that is inconsistent with real-world facts or user inputs, poses another challenge for robot task planning.”
BackgroundInfluentialLiu, F., Ju, Q., Zheng, Q., & Peng, Y. (2024) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2024.101452 · Cited by 45
Jin, Y., & Ma, J. (2024) · Sustainable Cities and Society · doi:10.1016/j.scs.2024.105940 · Cited by 41
Choi, S., & Kim, H. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-13107-x · Cited by 51
“This is due to the inherent limitations of the underlying LLM, which can suffer from "hallucinations," or the generation of incorrect or irrelevant information (Ji et al., 2023).”
Wang, Z., Liu, Z., Lu, J. W. Z., & Lu, J. H. (2025) · Journal of Building Engineering · doi:10.1016/j.jobe.2025.112189 · Cited by 49
Men, C., Han, Y., Wang, P., Tao, J., & Huang, C. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3550999 · Cited by 51
“…as research delves deeper, it has been discovered that in fields requiring deep and interpretable reasoning, particularly in fault diagnosis scenarios that necessitate continual knowledge updates, LLMs often struggle with hallucinatory answers, leading to suboptimal results or even errors [20].”
A survey for large language models in biomedicine
Wang, C., Li, M., He, J., Wang, Z., Darzidehkalani, E., Chen, Z., Ye, J., Li, T., Su, Y., Ke, J., et al. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103268 · Cited by 77
Awosanya, O. D., Harris, A., Creecy, A., Qiao, X., Toepp, A. J., McCune, T., Kacena, M. A., & Ozanne, M. V. (2024) · Current Osteoporosis Reports · doi:10.1007/s11914-023-00855-x · Cited by 27
“The act of fabrication of information by AI has been termed as a “hallucination” or “artificial hallucina-tion” [15, 16].”
BackgroundJelodar, H., Bai, S., Hamedi, P., Mohammadian, H., Razavi-Far, R., & Ghorbani, A. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104390 · Cited by 27
ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing
Liu, R., & Shah, N. B. (2023) · arXiv · doi:10.48550/arxiv.2306.00622 · Cited by 23
Koga, S. (2023) · Korean Journal of Radiology · doi:10.3348/kjr.2023.0738 · Cited by 33
“A prominent limitation of LLMs, commonly referred to as “hallucination,” arises when they generate seemingly credible but fabricated information [5].”
BackgroundRetrieval-based Evaluation for LLMs: A Case Study in Korean Legal QA
Ryu, C., Lee, S., Pang, S., Choi, C., Choi, H., Min, M., & Sohn, J.-Y. (2023) · Natural Legal Language Processing Workshop (NLLP) · doi:10.18653/v1/2023.nllp-1.13 · Cited by 57
Cross-platform social dynamics: an analysis of ChatGPT and COVID-19 vaccine conversations
Alipour, S., Galeazzi, A., Sangiorgio, E., Avalle, M., Bojić, L., Cinelli, M., & Quattrociocchi, W. (2024) · Scientific Reports · doi:10.1038/s41598-024-53124-x · Cited by 45
“This comparison aims to clarify the differences in information dissemination dynamics across global topics.”
BackgroundKasthuri, V. S., Glueck, J., Pham, H., Daher, M., Balmaceno-Criss, M., McDonald, C. L., Diebo, B. G., & Daniels, A. H. (2024) · Journal of Bone and Joint Surgery · doi:10.2106/jbjs.23.00914 · Cited by 29
“Indeed, LLMs are known to “ hallucinate, ” or generate responses that are unfaithful to the underlying training material 4 .”
BackgroundLarge Language Models in Oncology: Revolution or Cause for Concern?
Caglayan, A., Slusarczyk, W., Rabbani, R. D., Ghose, A., Papadopoulos, V. P., & Boussios, S. (2024) · Current Oncology · doi:10.3390/curroncol31040137 · Cited by 30
“It should be noted that different strategies exist to overcome LLM hallucinations, which can be separated into two categories, data-related methods or modelling and interference methods [66].”
BackgroundAngel, M. C., Rinehart, J. B., Canneson, M. P., & Baldi, P. (2024) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000006892 · Cited by 50
Performance without understanding: How ChatGPT relies on humans to repair conversational trouble
Pütz, O., & Esposito, E. (2024) · Discourse & Communication · doi:10.1177/17504813241271492 · Cited by 47
“In closing, we discuss an example of a ‘hallucina-tion’ where that might be different: A hallucination is a text that appears to be plausible and grounded in real world contexts, ‘although it is actually hard to specify or verify the existence of such contexts’ (Ji et al. 2023, p. 3).”
Franc, J. M., Hertelendy, A. J., Cheng, L. T. W., Hata, R., & Verde, M. (2024) · Journal of Medical Internet Research · doi:10.2196/55648 · Cited by 45
“…LLMs are powerful and intuitive, they are not without shortcomings and have two major faults: (1) hallucinations or confabulations: LLMs can generate outputs, or “hallucinations,” that are syntactically correct and superficially plausible but factually inaccurate or entirely fabricated [2].”
Griewing, S., Lechner, F., Gremke, N., Lukac, S., Janni, W., Wallwiener, M., Wagner, U., Hirsch, M., & Kuhn, S. (2024) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-024-05964-3 · Cited by 26
“…knowledge graphs and doctoral decision trees of the breast cancer patient pathway into the newly developed SLM design concept to minimize the prevailing challenge of language model hallucination and optimize decision reliability and accuracy (Ji et al. 2022; Benary et al. 2023; Sorin et al. 2024).”
Large language models facilitating modern molecular biology and novel drug development
Liu, X., Lü, Z., Wang, T., & Liu, F. (2024) · Frontiers in Pharmacology · doi:10.3389/fphar.2024.1458739 · Cited by 33
Rong, R., Ma, S., Ren, N., Lin, Q., & Jia, N. (2025) · Frontiers of Engineering Management · doi:10.1007/s42524-025-4241-9 · Cited by 53
“Flaws and biases in the data, issues with architecture and strategies during training, and randomness in sampling and decoding constraints during inference can all lead to content that deviates from actual circumstances (Ji et al., 2023).”
Exploring RAG Solutions to Reduce Hallucinations in LLMs
AboulEla, S., Zabihitari, P., Ibrahim, N., Afshar, M., & Kashef, R. F. (2025) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon64521.2025.11014810 · Cited by 40
“To reduce hallucination in LLMs, a lot of research has been done in traditional NLG situations [18], [19].”
Hallucination Detection in Large Language Models with Metamorphic Relations
Yang, B., Mamun, M. A. A., Zhang, J. M., & Uddin, G. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3715735 · Cited by 68
Prompt engineering for accurate statistical reasoning with large language models in medical research
Vilakati, S. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1658316 · Cited by 35
Inventing with Machines: Generative AI and the Evolving Landscape of IS Research
Gopal, R. D., Li, J., Riemer, K., Sarker, S., Singh, P. V., Susarla, A., Bichler, M., & Thatcher, J. B. (2025) · Information Systems Research · doi:10.1287/isre.2025.editorial.v36.n4 · Cited by 58
Vavekanand, R., Laghari, A. A., & Kumar, T. (2026) · Iran Journal of Computer Science · doi:10.1007/s42044-025-00360-7 · Cited by 34
“A survey discusses LLM technical aspects, such as architecture and developmental stages, together with their medical capabilities [21].”
Ma, F., Chen, J., Dai, Z., Cai, F., & Hu, Y. (2026) · Water Research · doi:10.1016/j.watres.2026.125886 · Cited by 44
ChatGPT and Large Language Models in Healthcare: Opportunities and Risks
Ali, H., Qadir, J., Alam, T., Househ, M. S., & Shah, Z. (2023) · International Conference on Artificial Intelligence, Blockchain, and Internet of Things (AIBThings) · doi:10.1109/aibthings58340.2023.10291020 · Cited by 34
“Similarly, ChatGPT can make mistakes, including hallucinating non-factual information and providing biased advice [10].”
BackgroundChatGPT in Occupational Medicine: A Comparative Study with Human Experts
Padovan, M., Cosci, B., Petillo, A., Nerli, G., Porciatti, F., Scarinci, S., Carlucci, F., Dell’Amico, L., Meliani, N., Necciari, G., et al. (2024) · Bioengineering · doi:10.3390/bioengineering11010057 · Cited by 31
“Recognizing hallucinations is essential, but understanding how to mitigate their occurrence is equally crucial [39], while their mitigation remains an open question and is subject to numerous field studies [40,41].”
BackgroundClassification of Human- and AI-Generated Texts for English, French, German, and Spanish
Schaaff, K., Schlippe, T., & Mindner, L. (2023) · arXiv · doi:10.48550/arxiv.2312.04882 · Cited by 26
Wang, H., Zhao, S., Qiang, Z., Li, Z., Xi, N., Du, Y., Cai, M., Guo, H., Chen, Y., Xu, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.04175 · Cited by 26
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances
Zhang, Z., Fang, M., Chen, L., Namazi‐Rad, M., & Wang, Y.-X. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.516 · Cited by 117
RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
Shu, L., Luo, L., Hoskere, J., Zhu, Y., Liu, Y., Tong, S., Chen, J., & Meng, L. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29863 · Cited by 112
Kraft, A., & Soulier, E. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658981 · Cited by 25
Use of SNOMED CT in Large Language Models: Scoping Review
Chang, E., & Sung, S. (2024) · JMIR Medical Informatics · doi:10.2196/62924 · Cited by 49
“Moreover, numerous studies have demonstrated that LLMs struggle to recall facts and frequently encounter hallucinations, generating factually inaccurate statements [5,6].”
BackgroundAn Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration
Li, Y., Zhang, R., & Liu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72344-5_17 · Cited by 56
DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer
Wei, J., & Zhang, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681076 · Cited by 54
Huang, T.-Y., Hsieh, P.-H., & Chang, Y.-C. (2024) · JMIR Medical Education · doi:10.2196/59902 · Cited by 19
Mitigating Entity-Level Hallucination in Large Language Models
Su, W., Tang, Y., Ai, Q., Wang, C., Wu, Z., & Liu, Y. (2024) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3673791.3698403 · Cited by 65
Fostering effective hybrid human-LLM reasoning and decision making
Passerini, A., Gema, A. P., Minervini, P., Sayin, B., & Tentori, K. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1464690 · Cited by 52
A Comprehensive Survey of Fake Text Detection on Misinformation and LM-Generated Texts
Kwon, S.-C., & Jang, B. (2025) · IEEE Access · doi:10.1109/access.2025.3538805 · Cited by 37
Bullshit universities: the future of automated education
Sparrow, R., & Flenady, G. (2025) · AI & Society · doi:10.1007/s00146-025-02340-8 · Cited by 69
“10 To do so, though, given the tendency of AI systems to ‘hallucinate’ (Ji et al. 2023), students must be able to check the quality of the outputs of the AI in line with disciplinary standards (Bearman and Ajjawi 2023).”
Friction: Deciphering Writing Feedback into Writing Revisions through LLM-Assisted Reflection
Zhang, C., Ju, K., Bidoshi, P., Yen, Y.-C. G., & Rzeszotarski, J. M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714316 · Cited by 49
Nishisako, S., Higashi, T., & Wakao, F. (2025) · JMIR Cancer · doi:10.2196/70176 · Cited by 47
“These problems may have been caused by errors in data retrieval by the LLM or by vectorization or structuring in the knowledge database [22].”
InfluentialDissecting Corporate Culture Using Generative AI
Li, K., Mai, F., Shen, R., Yang, C., & Zhang, T. (2023) · Review of Financial Studies · doi:10.1093/rfs/hhaf081 · Cited by 99
Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
Liang, C., Deng, Y., Bian, Y., Qin, Z., Wu, B., Chua, T., & Wong, K. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.390 · Cited by 93
Transforming nursing with large language models: from concept to practice
Woo, B., Huynh, T., Tang, A., Bui, N., Nguyen, G., & Tam, W. (2024) · European Journal of Cardiovascular Nursing · doi:10.1093/eurjcn/zvad120 · Cited by 33
Innovations in Medicine: Exploring ChatGPT’s Impact on Rare Disorder Management
Zampatti, S., Peconi, C., Megalizzi, D., Calvino, G., Trastulli, G., Cascella, R., Strafella, C., Caltagirone, C., & Giardina, E. (2024) · Genes · doi:10.3390/genes15040421 · Cited by 37
“Another described ChatGPT hallucination is in the production of medical notes, sometimes fabricating patient features (i.e., it generates BMI score, without height and weight data) [23,54].”
BackgroundAdaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection
Lai, Z., Zhang, X., & Chen, S. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651296 · Cited by 65
“Firstly, GPT and other high-level language generation models can generate realistic text, which may be used to create and disseminate misleading information [19], fake news, or harmful content.”
BackgroundSood, A. K., Zeadally, S., & Hong, E. (2025) · Computers and Electrical Engineering · doi:10.1016/j.compeleceng.2025.110307 · Cited by 33
Technological folie à deux: Feedback Loops Between AI Chatbots and Mental Illness
Dohnány, S., Kurth-Nelson, Z., Spens, E., Luettgau, L., Reid, A., Gabriel, I., Summerfield, C., Shanahan, M., & Nour, M. M. (2025) · arXiv · doi:10.48550/arxiv.2507.19218 · Cited by 26
Using GitHub Copilot for Test Generation in Python: An Empirical Study
Haji, K. E., Brandt, C., & Zaidman, A. (2024) · doi:10.1145/3644032.3644443 · Cited by 58
Artificial Dreams: Surreal Visual Storytelling as Inquiry Into AI 'Hallucination'
Halperin, B. A., & Lukin, S. M. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3660685 · Cited by 35
AI-Assisted Code Authoring at Scale: Fine-Tuning, Deploying, and Mixed Methods Evaluation
Murali, V., Maddila, C., Ahmad, I., Bolin, M., Cheng, D., Ghorbani, N., Fernandez, R., Nagappan, N., & Rigby, P. C. (2024) · Proceedings of the ACM on software engineering. · doi:10.1145/3643774 · Cited by 114
RAGVA: Engineering retrieval augmented generation-based virtual assistants in practice
Yang, R., Fu, M. C., Tantithamthavorn, C. K., Arora, C., Vandenhurk, L., & Chua, J. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112436 · Cited by 49
Agent-OM: Leveraging LLM Agents for Ontology Matching
Qiang, Z., Wang, W., & Taylor, K. L. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3712221.3712222 · Cited by 80
Stephan, D., Bertsch, A., Schumacher, S., Puladi, B., Burwinkel, M., Al‐Nawas, B., Kämmerer, P. W., & Thiem, D. G. E. (2025) · Journal of Medical Internet Research · doi:10.2196/73337 · Cited by 44
“LLMs are known to occasionally generate inaccurate or fabricated content, which is often referred to as hallucinations [16,17].”
Are ChatGPT and other pretrained language models good parasitologists?
Šlapeta, J. (2023) · Trends in Parasitology · doi:10.1016/j.pt.2023.02.006 · Cited by 24
Opportunities and Challenges in Neural Dialog Tutoring
Mačina, J., Daheim, N., Wang, L., Sinha, T., Kapur, M., Gurevych, I., & Sachan, M. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.173 · Cited by 76
A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection
Yang, S., Sun, R., & Wan, X. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.256 · Cited by 84
Jiang, L., Jung, C., Phutane, M., Stangl, A. J., & Azenkot, S. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642238 · Cited by 59
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.




