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 901–1,000 of 4,837
Medical multimodal large language models: A systematic review
Hu, Y., Xu, C., Lin, B., Yang, W., & Tang, Y. Y. (2025) · Intelligent Oncology · doi:10.1016/j.intonc.2025.09.005 · Cited by 14
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
Zhang, J., Bai, Y., Lv, X., Gu, W., Liu, D., Zou, M., Cao, S., Hou, L., Dong, Y., Feng, L., et al. (2024) · arXiv · doi:10.48550/arxiv.2409.02897 · Cited by 14
Wang, X., Huey, S. L., Sheng, R., Mehta, S., & Wang, F. (2025) · Campbell Systematic Reviews: Better Evidence for a Better World · doi:10.1002/cl2.70073 · Cited by 13
“Unlike standard prompting, which relies solely on a model's pretrained knowledge (and can be outdated due to the LLM's training cutoff), RAG dynamically retrieves and integrates up ‐ to ‐ date, domain ‐ specific information into prompts.”
Wu, W., Guo, Y., Li, Q., & Jia, C. (2024) · Liver International · doi:10.1111/liv.16112 · Cited by 22
“35 In these experiments, we provided LLMs with an explicit prompt and asked them to align responses with a clearly defined template, which might be less prone to hallucinations than ‘open’ questions.”
Understanding question-answering systems: Evolution, applications, trends, and challenges
Farea, A., & Emmert‐Streib, F. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110997 · Cited by 21
Calderón, R., & Herrera, F. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-04650-0 · Cited by 23
“Transparency, explainability, Evaluation & Auditing, controllability, opacity and black box issues Anderljung et al., 2023; Castelvecchi, 2016; Hendrycks et al., 2023; Ji et al., 2023; Mökander & Floridi, 2023; Wang et al., 2023.”
When cutting edge meets silver tongue: Understanding the word-of-machine effect on travel decisions
Sun, D., Wong, I. A., Xiong, X., & Li, S. (2025) · Tourism Management · doi:10.1016/j.tourman.2025.105271 · Cited by 23
Chen, R., Gao, B., Qin, G., Chang, C., Kang, Y., Ren, H., Zou, D., Ma, Q., & Woo, W. L. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3588620 · Cited by 17
“A RTIFICIAL intelligence (AI) has become ubiquitous, with huge applications in areas such as autonomous driving [1], natural language generation [2], and nondestructive testing (NDT) [3].”
Marandi, S., Hu, Y.-S., & Modarres, M. (2025) · Applied Sciences · doi:10.3390/app15179428 · Cited by 13
Ilić, N., & Sarajlija, A. (2025) · Journal of Personalized Medicine · doi:10.3390/jpm15090407 · Cited by 19
Shen, K., & Kejriwal, M. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112253 · Cited by 16
Large Language Models for Cybersecurity Intelligence, Threat Hunting, and Decision Support
Ren, S., & Chen, S. (2025) · Jisuanji shenghuojia. · doi:10.54097/7ysr5k17 · Cited by 40
“The phenomenon of hallucination, where models generate convincing but factually incorrect information, poses unique risks in security applications where accuracy directly impacts defense effectiveness [57].”
Li, M., Zhan, Z., Yang, H., Xiao, Y., Zhou, H., Huang, J., & Zhang, R. (2025) · Science Advances · doi:10.1126/sciadv.adr1443 · Cited by 42
“Despite demonstrating impressive general capabilities ( 3 ), these models still face substantial challenges, including factual hallucination ( 4 ) and absence of newly uploaded knowledge ( 5 ).”
Hosseini, S. H., Zolghadr‐Asli, B., Tenkanen, H., Madani, K. M., Matin, M. A., Demir, İ., Ostfeld, A., Singh, V. P., & Savic, D. A. (2025) · Water Research · doi:10.1016/j.watres.2025.125157 · Cited by 18
Kirk, H. R., Bean, A., Vidgen, B., Röttger, P., & Hale, S. A. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.148 · Cited by 91
Merging Generated and Retrieved Knowledge for Open-Domain QA
Zhang, Y., Khalifa, M., Logeswaran, L., Lee, M., Lee, H., & Wang, L. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.286 · Cited by 63
Counterexample Guided Inductive Synthesis Using Large Language Models and Satisfiability Solving
Jha, S. K., Jha, S., Lincoln, P. D., Bastian, N. D., Velasquez, A., Ewetz, R., & Neema, S. K. (2023) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom58377.2023.10356332 · Cited by 28
“However, LLMs are prone to generating factually incorrect or contextually inappropriate responses, also referred to as hallucinations [3], [4].”
BackgroundThe Pitfalls of Defining Hallucination
Deemter, K. V. (2024) · Computational Linguistics · doi:10.1162/coli_a_00509 · Cited by 13
Use of ChatGPT in Higher Education: A Study with Graduate Students
Costa, R., Costa, A. L., & Carvalho, A. A. A. (2024) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-031-52296-3_7 · Cited by 19
Can ChatGPT support software verification?
Janßen, C., Richter, C., & Wehrheim, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-57259-3_13 · Cited by 45
Quevedo, E., Abdelfattah, A. S., Rodriguez, A., Yero, J., & Cerny, T. (2024) · SN Computer Science · doi:10.1007/s42979-024-02664-0 · Cited by 15
“Hallucinations are critical limitations in current state-of-the-art LLMs, including ChatGPT [15, 32, 51].”
Do LLMs Meet the Needs of Software Tutorial Writers? Opportunities and Design Implications
Bhat, A., Shrivastava, D., & Guo, J. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3660692 · Cited by 19
Integrating Visual Context Into Language Models for Situated Social Conversation Starters
Janssens, R., Wolfert, P., Demeester, T., & Belpaeme, T. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3428704 · Cited by 20
“Hallucination is an often-observed phenomenon in deep learning based natural language generation [56].”
Zhang, D., Ma, Z., Gong, R., Lian, L., Li, Y., He, Z., Han, Y., Hui, J., Huang, J., Jiang, J., et al. (2024) · Journal of Medical Internet Research · doi:10.2196/58741 · Cited by 21
“Previously, large language models faced the challenge of hallucination, presenting presumably persuasive results that were not based on the input [20,21].”
Herman, E., Nicholas, D., Abrizah, A., Revez, J. M. R., Bravo, B. R., Świgoń, M., Clark, D., Xu, J., & Watkinson, A. (2024) · Learned Publishing · doi:10.1002/leap.1623 · Cited by 17
“The most talked-about worry is the so-called hallucinations — texts that give the impression of being fl uent and natural, despite being unfaithful and nonsensical (Ji et al., 2023), but the literature lists quite a few additional problems.”
Sufi, F. K. (2024) · Journal of Economy and Technology · doi:10.1016/j.ject.2024.09.001 · Cited by 17
Qlarify: Recursively Expandable Abstracts for Dynamic Information Retrieval over Scientific Papers
Fok, R., Chang, J. C., August, T., Zhang, A. X., & Weld, D. S. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676397 · Cited by 52
Political biases and inconsistencies in bilingual GPT models—the cases of the U.S. and China
Zhou, D., & Zhang, Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-76395-w · Cited by 42
“A larger comparative study is warranted to compare more languages that the GPT supports, especially the languages that are associated with a distinct cultural and political system, to verify the potential in-group favoritism of GPT models and other LLMs.”
InfluentialRetrieval In Decoder benefits generative models for explainable complex question answering
Feng, J., Wang, Q., Qiu, H., & Liu, L. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106833 · Cited by 19
A Joint LLM-KG System for Disease Q&A
Sukhwal, P. C., Rajan, V., & Kankanhalli, A. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3514659 · Cited by 21
“However, they need large amounts of data for fine-tuning, provide multiple potential answers from which it is difficult to choose the final answer [22], and are prone to hallucinations i.e., factual inconsistencies [23].”
Hannah, G., Sousa, R. T., Dasoulas, I., & d’Amato, C. (2024) · Journal of Web Semantics · doi:10.1016/j.websem.2024.100843 · Cited by 24
Learned, uncertainty-driven adaptive acquisition for photon-efficient scanning microscopy
Ye, C. T., Han, J., Liu, K., Angelopoulos, A. N., Griffith, L. G., Monakhova, K., & You, S. (2024) · Optics Express · doi:10.1364/oe.542640 · Cited by 17
Prompt Injection Attacks in Defended Systems
Khomsky, D., Maloyan, N., & Nutfullin, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-80853-1_30 · Cited by 13
“This paper investigates the vulnerabilities and risks related to LLMs, focusing on issues such as hallucinations [1], biases [2], [3], and susceptibility to malicious attacks [4], [5], [6].”
BackgroundGIA: LLM-Enabled Generative Intent Abstraction to Enhance Adaptability for Intent-Driven Networks
Kou, S., Yang, C., & Gurusamy, M. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3545589 · Cited by 21
“However, since the knowledge in the pre-trained LLMs might be incomplete, incorrect, and outdated, they often generate factually incorrect answers due to their lack of intrinsic knowledge about specific tasks [29].”
Shaikh, T. A., Rasool, T., & Mir, W. A. (2025) · Computer Standards & Interfaces · doi:10.1016/j.csi.2025.104005 · Cited by 22
Shin, M., Song, J., Kim, M.-G., Yu, H. W., Choe, E. K., & Chai, Y. J. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14072450 · Cited by 20
“The issue of hallucinations—where the model produces fabricated content—further complicates their use [9,10].”
ChatGPT in the field of scientific publication – Are we ready for it?
Subbaramaiah, M. T., & Shanthanna, H. (2023) · Indian Journal of Anaesthesia · doi:10.4103/ija.ija_294_23 · Cited by 16
Semantic Analysis of Phishing Emails Leading to Ransomware with ChatGPTPreprint
Fujima, H., Takeuchi, K., & Kumamoto, T. (2023) · Research Square · doi:10.21203/rs.3.rs-3670198/v1 · Cited by 14
GPT-Neo-CRV: Elevating Information Accuracy in GPT-Neo with Cross-Referential ValidationPreprint
Xiong, X., & Zheng, M. (2024) · doi:10.36227/techrxiv.170473976.61241065/v1 · Cited by 15
Omar, M., Sorin, V., Collins, J. D., Reich, D., Freeman, R., Gavin, N. P., Charney, A. W., Stump, L. S., Bragazzi, N. L., Nadkarni, G. N., et al. (2025) · medRxiv · doi:10.1101/2025.03.18.25324184 · Cited by 13
Learning visual language models for video understanding
Yang, A. (2023) · theses.fr (ABES) · doi:10.70675/802872a7z8092z4556za1fdz2c7af45f0e72 · Cited by 26
APPA: Recoverable Information-Flow Control for Real-World LLM Agents
Kravchenko, A., Liventsev, V., Konstantinov, I., Iskhakov, I., & Kukuy, M. (2026) · arXiv · Cited by 13
Next Steps for Human-Centered Generative AI: A Technical Perspective
Chen, X. '., Burke, J., Du, R., Hong, M. K., Jacobs, J., Laban, P., Li, D., Peng, N., Willis, K. D. D., Wu, C.-S., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.15774 · Cited by 13
McCrary, M. R., Galambus, J., & Chen, W. (2024) · Journal of Cutaneous Pathology · doi:10.1111/cup.14631 · Cited by 12
Adapting to the AI Era: ChatGPT in the Classroom
Spindel, J. E., & Ackerman, J. (2024) · Journal of Political Science Education · doi:10.1080/15512169.2024.2414017 · Cited by 12
EvAlignUX: Advancing UX Evaluation through LLM-Supported Metrics Exploration
Zheng, Q., Chen, M., Sharma, P., Tang, Y., Oswal, M., Liu, Y., & Huang, Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714045 · Cited by 30
A descriptive phenomenological study of postgraduate nursing students' experiences with ChatGPT
Aslan, F. (2025) · Journal of Professional Nursing · doi:10.1016/j.profnurs.2025.05.004 · Cited by 15
An intelligent guided troubleshooting method for aircraft based on HybirdRAG
Xie, X., Tang, X., Gu, S., & Cui, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-02643-2 · Cited by 26
Translating code with Large Language Models and human-in-the-loop feedback
Siano, G. D. D., Fasolino, A. R., Sperlí, G., & Vignali, A. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107785 · Cited by 19
Extracting Formal Specifications From Documents Using LLMS for Test Automation
Li, H., Dong, Z., Wang, S., Hui, Z., Shen, L., Peng, X., & She, D. (2025) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1109/icpc66645.2025.00039 · Cited by 21
“We attribute these deficiencies to the inherent limitations of LLM, including their limited processing and expressive capabilities [19], [20], as well as their propensity to hallucination [21].”
When LLMs Hallucinate: Examining the Effects of Erroneous Feedback in Math Tutoring Systems
Steinbach, M., Bhandari, S., Meyer, J., & Pardos, Z. A. (2025) · Proceedings of the Twelfth ACM Conference on Learning @ Scale · doi:10.1145/3698205.3729555 · Cited by 12
Wang, C. H., Jia, D., Wang, W., Ngoduy, D., Peng, B., & Wang, J. (2025) · Communications in Transportation Research · doi:10.1016/j.commtr.2025.100211 · Cited by 19
Traditional agroforestry systems in Europe revisited: a systematic review
Hang, L. T., Bonari, G., Sauerwein, M., Plieninger, T., & Zerbe, S. (2025) · Agroforestry Systems · doi:10.1007/s10457-025-01335-0 · Cited by 22
“While Large Language Models (LLMs) are increasingly used for information retrieval despite their lack of transparency and tendency to generate unverifiable content (Ji et al. 2023), systematic reviews remain essential for transparent and reproducible synthesis (Page et al. 2021).”
Jeon, S., Lee, S., Kim, E. H., Eun, J., Lee, K., Lim, H., & Lee, J. (2025) · JMIR Formative Research · doi:10.2196/72553 · Cited by 29
“Widely adopted generative AI chatbots, such as ChatGPT and Gemini, often exhibit hallucination and tend to deliver overly generalized responses that lack the specificity required for clinical use [31,38,45,65,66].”
Memduhoğlu, A., Fulman, N., Polat, N., & Atas, T. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130171 · Cited by 17
Mansurova, A., Tleubayeva, A., Nugumanova, A., Shomanov, A., & Şeker, Ş. E. (2025) · Information · doi:10.3390/info16110943 · Cited by 20
“Large language models have a well-documented tendency to hallucinate—that is, to produce fluent but factually incorrect information [14,18].”
Developing a Framework for Auditing Large Language Models using Human-in-the-loop
Amirizaniani, M., Lavergne, A., Snell Okada, E., Chadha, A., Roosta, T., & Shah, C. (2025) · Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region · doi:10.1145/3767695.3769514 · Cited by 16
CTI-Thinker: an LLM-driven system for CTI knowledge graph construction and attack reasoning
Yang, X., Zhong, R., Chen, Y., Peng, G., Yao, D., Chen, C., Wang, C., Zhang, D., Zhou, Y., & Yang, Z. (2026) · Cybersecurity · doi:10.1186/s42400-025-00505-y · Cited by 23
“First, lacking external knowledge retrieval, they are prone to hallucinations that deviate from factual information (Ji et al. 2023; Huang et al. 2025).”
Amalfitano, D., Metzger, A., Autili, M., Fulcini, T., Hey, T., Keim, J., Pelliccione, P., Scotti, V., Koziolek, A., Mirandola, R., et al. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3788879 · Cited by 33
KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection
Choi, S.-H., Fang, T., Wang, Z., & Song, Y. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.867 · Cited by 80
Impact of Co-occurrence on Factual Knowledge of Large Language Models
Kang, C., & Choi, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.518 · Cited by 78
AmbiFC : Fact-Checking Ambiguous Claims with Evidence
Glockner, M., Staliūnaitė, I., Thorne, J., Vallejo, G., Vlachos, A., & Gurevych, I. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00629 · Cited by 89
“verification-real-world-info-needs generation tasks, including information-seeking dialogues (Dziri et al., 2022; Ji et al., 2023).”
Navigating Challenges and Technical Debt in Large Language Models Deployment
Menshawy, A., Nawaz, M. Z., & Fahmy, M. (2024) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3642970.3655840 · Cited by 24
Exploring the Feasibility of GPT-4 as a Data Extraction Tool for Renal Surgery Operative Notes
Hsueh, J. Y., Nethala, D., Singh, S. M., Hyman, J. A., Gelikman, D. G., Linehan, W. M., & Ball, M. W. (2024) · Urology Practice · doi:10.1097/upj.0000000000000599 · Cited by 13
“17 In addition to the variables themselves, how the variables are written in our notes could have affected our results.”
Zhang, D., Zhang, X., Bansal, C., Las-Casas, P., Fonseca, R., & Rajmohan, S. (2024) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3663529.3663858 · Cited by 43
The Impact of LLM Hallucinations on Motor Skill Learning: A Case Study in Badminton
Qiu, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3444783 · Cited by 27
“LLMs like ChatGPT and GPT-4 often generate content that is meaningless or unreal, resembling the characteristics of the psychological phenomenon known as LLM hallucination [7], [35], [58], [59].”
BackgroundByun, J., Kim, B., Cha, K.-A., & Lee, E. (2024) · Applied Sciences · doi:10.3390/app14177995 · Cited by 14
Evaluation of Question-Answering Based Text Summarization using LLM Invited Paper
Ding, J., Nguyen, H., & Chen, H. (2024) · IEEE International Conference on Artificial Intelligence Testing (AITest) · doi:10.1109/aitest62860.2024.00025 · Cited by 21
The Longtail Impact of Generative AI on Disinformation: Harmonizing Dichotomous Perspectives
Lucas, J. S., Maung, B. M., Tabar, M., McBride, K., & Lee, D. (2024) · IEEE Intelligent Systems · doi:10.1109/mis.2024.3439109 · Cited by 22
“Ji et al. 38 identified two types of hallucinations: intrinsic (the model’s output contradicts the source content) and extrinsic (the model’s output cannot be verified from the source content).”
BackgroundZeng, Q., Bai, Y., Tan, Z., Feng, S., Liang, Z., Zhang, Z., & Jiang, M. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679608 · Cited by 60
Automatic instantiation of assurance cases from patterns using large language models
Odu, O., Belle, A. B., Wang, S., Kpodjedo, S., Lethbridge, T. C., & Hemmati, H. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112353 · Cited by 28
Jiang, B., Wang, Y., Luo, Y., He, D., Cheng, P., & Gao, L. (2024) · IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg63256.2024.00026 · Cited by 44
Kumar, S., & Malhotra, D. (2025) · Tourism Recreation Research · doi:10.1080/02508281.2025.2503997 · Cited by 19
“In the context of GAI, AI hallucinations, are responses produced by AIs, such as language models, that portray false or fabricated data as fact (Ji et al., 2023).”
Aplicaciones de inteligencia artificial generativa en la transformación digital empresarial
Galarza-Sánchez, P. C., Boné-Andrade, M. F., & Bravo, V. J. P. (2023) · Revista Científica Ciencia y Método · doi:10.55813/gaea/rcym/v1/n1/8 · Cited by 25
A Survey on Unifying Large Language Models and Knowledge Graphs for Biomedicine and Healthcare
Xu, R., Jiang, P., Luo, L., Xiao, C., Cross, A., Pan, S., Sun, J., & Yang, C. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736556 · Cited by 38
“Studies have also revealed the limitations of LLMs regarding their lack of knowledge [5], fuzzy inference [6], and hallucination [7].”
Miceli Barone, A. V., Barez, F., Cohen, S. B., & Konstas, I. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.19 · Cited by 12
Slobodkin, A., Goldman, O., Caciularu, A., Dagan, I., & Ravfogel, S. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.220 · Cited by 145
Reliable Text-to-SQL with Adaptive Abstention
Chen, K., Chen, Y., Koudas, N., & Yu, X. (2025) · Proceedings of the ACM on Management of Data · doi:10.1145/3709719 · Cited by 12
Learning Fine-Grained Grounded Citations for Attributed Large Language Models
Huang, L., Feng, X., Ma, W., Gu, Y., Zhong, W., Feng, X., Yu, W., Peng, W., Tang, D., Tu, D., et al. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.838 · Cited by 12
Sparks of Large Audio Models: A Survey and Outlook
Latif, S., Shoukat, M., Shamshad, F., Usama, M., Ren, Y., Cuayáhuitl, H., Wang, W., Zhang, X., Togneri, R., Cambria, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.12792 · Cited by 17
“Ji et al. [88] divided hallucination into two categories: intrinsic hallucinations and extrinsic hallucinations.”
BackgroundChatbot-assisted quantum chemistry for explicitly solvated molecules
(2025) · doi:10.1039/d4sc08677e · Cited by 11
Differential effects of GPT-based tools on comprehension of standardized passages
Etkin, H., Etkin, K., Carter, R. E. B., & Rolle, C. E. (2025) · Frontiers in Education · doi:10.3389/feduc.2025.1506752 · Cited by 29
Shvetsova, O. A., Katalshov, D., & Lee, S.-K. (2025) · Applied Sciences · doi:10.3390/app15137298 · Cited by 26
Tumedei, G., Ceccarini, C., Jiménez-Navarro, I. C., & Prandi, C. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735722 · Cited by 14
Generating SysML Behavior Models via Large Language Models: an Empirical Study
Wang, Y., Ge, N., Liu, J., Cao, Z., Chen, Z., & Hu, C. (2025) · Asia-Pacific Symposium on Internetware · doi:10.1145/3755881.3755926 · Cited by 22
Elbasheer, M., Laili, Y., Longo, F., Solina, V., Tao, Y., Veltri, P., Zhang, Y., & Zhang, L. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02732-z · Cited by 38
“A key innovation in this approach is implementing a Four-Step Knowledge Extraction Pipeline that applies established prompt engineering principles to mitigate common LLM limitations such as hallucinations, inconsistencies, and ambiguous outputs (Ji et al., 2023; Tonmoy et al., 2024).”
Hallucinations in Generative AI: Epistemic Risks for Learners in Educational Applications
Virvou, M. K., Tsihrintzis, G. A., & Tsichrintzi, E.-A. (2025) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa66859.2025.11311276 · Cited by 23
“Ji and colleagues [52] provide a relevant survey.”
Gong, C., Wei, Z., Tao, W., & Miao, D. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104614 · Cited by 13
Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
Liu, F., Liu, Y., Shi, L., Yang, Z., Zhang, L., Lian, X., Li, Z., & Ma, Y. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3657432 · Cited by 412
“Hallucinations refers to the phenomenon that LLMs might produce nonsensical or unfaithful outputs to the provided source content [24], [28], which can poses a potential risk in deploying LLMs across various applications.”
InfluentialLLM-enabled multi-agent framework for natural language interaction with graph-based digital twins
Pan, Y., Wang, M., Lu, L., Lamsal, R., Parn, E. A., Sisi Zlatanova, B., & Brilakis, I. (2026) · Automation in Construction · doi:10.1016/j.autcon.2026.106791 · Cited by 28
Studying Psychosis Using Natural Language Generation: A Review of Emerging Opportunities
Palaniyappan, L. K., Benrimoh, D. A., Voppel, A., & Rocca, R. (2023) · Biological Psychiatry Cognitive Neuroscience and Neuroimaging · doi:10.1016/j.bpsc.2023.04.009 · Cited by 17
How Can IJDS Authors, Reviewers, and Editors Use (and Misuse) Generative AI?
Shmueli, G., Colosimo, B. M., Martens, D., Padman, R., Saar‐Tsechansky, M., Sheng, O. R. L., Street, W. N., & Tsui, K. (2023) · INFORMS Journal on Data Science · doi:10.1287/ijds.2023.0007 · Cited by 18
ChatGPT: An Evaluation of AI-Generated Responses to Commonly Asked Pregnancy Questions
Wan, C. J. K., Cadiente, A., Khromchenko, K., Friedricks, N., Rana, R., & Baum, J. D. (2023) · Open Journal of Obstetrics and Gynecology · doi:10.4236/ojog.2023.139129 · Cited by 17
He, W., Ma, H., Li, S., Hui, D., Zhang, H., & Feng, J. (2023) · Applied Sciences · doi:10.3390/app132212208 · Cited by 16
“LLMs suffer from severe hallucination or overgeneration issues [39], so the usage of large models alone cannot achieve good performance on subtasks.”
BackgroundChatGPT: a reliable fertility decision-making tool?
Beilby, K. H., & Hammarberg, K. (2024) · Human Reproduction · doi:10.1093/humrep/dead272 · Cited by 18
“Additionally, ‘hallucinations’ may occur in AI-derived information with the generation of seemingly sensical text, but which has incorrect, inaccurate, or non-sensical meaning within a certain context (Ji et al. , 2023).”
BackgroundCross-Modal Retrieval for Knowledge-Based Visual Question Answering
Lerner, P., Ferret, O., & Guinaudeau, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56027-9_26 · Cited by 42
Manifestations of xenophobia in AI systems
Tomašev, N., Maynard, J. L., & Gabriel, I. (2024) · AI & Society · doi:10.1007/s00146-024-01893-4 · Cited by 25
“…al. 2023; Long 2023; Weng et al. 2023; Lu et al. 2023; Taylor 2023; Zhang et al. 2023; Besta et al. 2023), there is still a degree of skepticism on these nascent capabilities (Xu et al. 2023; Huang et al. 2023) and additional challenges that remain to be overcome (Ji et al. 2023; Shi et al. 2023).”
Fault Diagnosis and System Maintenance Based on Large Language Models and Knowledge Graphs
Li, Y., He, Y., Lian, R., & Guo, Q. (2023) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai60863.2023.10489566 · Cited by 15
“"Hallucination" refers to generating content that is meaningless or unfaithful to the sources provided [2].”
BackgroundAn Empathic GPT-Based Chatbot to Talk About Mental Disorders With Spanish Teenagers
Mármol-Romero, A. M., García-Vega, M., García-Cumbreras, M. Á., & Montejo-Ráez, A. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2344355 · Cited by 11
“Regarding major challenges and limitations, some of them are related to the undesired behaviour of LLMs, like bias [43] or hallucination [44].”
Yin, M., Wang, E., Ng, C., & Xiao, R. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642253 · Cited by 25
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.




