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 2,001–2,100 of 4,844
Generative AI for Wireless Communication and Sensing: Toward Unified Foundation Models
Yang, Z., Chi, G., Wu, C., Liu, H., Gao, Y., Liu, Y., Eldar, Y. C., Xu, J., & Han, T. X. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3704192 · Cited by 3
“…and inference costs of LLMs remain prohibitively high for deployment on resource-constrained communication nodes and sensing devices, while hallucination may produce outputs that are inconsistent with physical reality and thus undermine reliability in safety-critical tasks [240], [260], [261].”
Melville, G., Ghiassi, D., Inthathirath, S., et al. (2026) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2026.198013 · Cited by 2
Is your prompt poisoning code? Defect induction rates and security mitigation strategies
Wang, B., Zhong, Y., Wan, M., Yu, W., Ouyang, Y., Huang, Y., Wu, H., & Li, H. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10866-8 · Cited by 7
“…advanced prompting strate - gies–such as chain-of-thought reasoning and self-correction (Madaan et al. 2023; Fu et al. 2022 ) effectively mitigate security risks introduced by low-normativity prompts, thereby offering developers and LLM researchers actionable guidance for safer code generation.”
Dong, Y., Zhang, T., & Tian, X.-Y. (2026) · Journal of Hospitality and Tourism Technology · doi:10.1108/jhtt-11-2025-1080 · Cited by 3
Understanding on the Edge: LLM-generated Boundary Test Explanations
Akbarova, S., Dobslaw, F., & FELDT, R. H. (2026) · doi:10.1145/3793654.3793754 · Cited by 5
Are LLMs reliable code reviewers? systematic overcorrection in requirement conformance judgement
Jin, H., & Chen, H. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00638-5 · Cited by 18
“Nevertheless, LLMs are known to exhibit hallucinations and systematic biases [11], and prompt “enhancements” may unintentionally shift the model’s error profile rather than uniformly improving accuracy.”
Кузнецов, И. И. (2026) · Modelirovanie, optimizaciâ i informacionnye tehnologii. · doi:10.26102/2310-6018/2026.57.6.020 · Cited by 2
The digital therapist? LLMs and the future of clinical dialogue
Shi, E. R., Pei, R., & Barceló-Coblijn, L. (2026) · Language and Health · doi:10.1016/j.laheal.2026.100086 · Cited by 5
Otis, N. G., Clarke, R. P., Delecourt, S., Holtz, D., & Koning, R. M. (2026) · Management Science · doi:10.1287/mnsc.2024.06909 · Cited by 48
Tutorial: guidance on the use of large language models for medical research
Jin, Q., Wan, N., Leaman, R., Tian, S., Wang, Z., Yang, Y., Wang, Z., Xiong, G., Lai, P.-T., Zhu, Q. L., et al. (2026) · Nature Protocols · doi:10.1038/s41596-026-01408-z · Cited by 16
Salem, M. A. (2026) · Computers · doi:10.3390/computers15080478 · Cited by 2
Towards Efficient Coarse-grained Dialogue Response Selection
Lan, T., Mao, X.-L., Wei, W., Gao, X., & Huang, H. (2023) · ACM Transactions on Information Systems · doi:10.1145/3597609 · Cited by 2
Bang, J., & Cho, B. C. (2023) · Journal of Broadcast Engineering · doi:10.5909/jbe.2023.28.4.400 · Cited by 4
Can readers spot the AI impostor in healthcare writing?
Bourré, N. (2023) · Medical Writing · doi:10.56012/fwhk6920 · Cited by 2
Evaluation of ChatGPT Applicability to Learning Quantum Physics
Stefańska, A., Stefański, T. P., & Czubenko, M. (2023) · International Conference on Signal Processing and Communication Systems · doi:10.1109/icspcs58109.2023.10261132 · Cited by 5
The hallucinating chatbot ‘ChatGPT’ poorly estimates real bird commonness
Żmihorski, M. (2023) · Biological Conservation · doi:10.1016/j.biocon.2023.110371 · Cited by 4
Is the Answer in the Text? Challenging ChatGPT with Evidence Retrieval from Instructive Text
Henning, S., Anthonio, T., Zhou, W. L., Adel, H., Mesgar, M., & Friedrich, A. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.949 · Cited by 3
Axiomatic Preference Modeling for Longform Question Answering
Rosset, C., Zheng, G., Dibia, V. C., Awadallah, A., & Bennett, P. N. (2023) · Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.702 · Cited by 9
Entity-Based Evaluation of Political Bias in Automatic Summarization
Zhou, K., & Tan, C. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.696 · Cited by 5
USB: A Unified Summarization Benchmark Across Tasks and Domains
Krishna, K., Gupta, P., Ramprasad, S., Wallace, B., Bigham, J. P., & Lipton, Z. C. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.592 · Cited by 11
Aligning Documentation and Q&A Forum through Constrained Decoding with Weak Supervision
Pudari, R., Zhou, S., Ahmed, I., Dai, Z., & Zhou, S. (2023) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme58846.2023.00043 · Cited by 5
“Importantly, as LLMs generate free-form text, it is unclear how to use them to retrieve an existing piece of official documentation for a question instead of generating a new, hallucinated text [20].”
BackgroundAn Inquirer-Responder Architecture Using LLMs: Emulating Virtual Hearing Q&A in Education
Nakanishi, T. (2023) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat59888.2023.00088 · Cited by 4
Thai Knowledge-Augmented Language Model Adaptation (ThaiKALA)
Ruangchutiphophan, P., Saetia, C., Ayutthaya, T. S. N., & Chalothorn, T. (2023) · International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP) · doi:10.1109/isai-nlp60301.2023.10355001 · Cited by 3
“One of the problems is that knowledge in the model depends on the training data that is used to pre-train, so non-updated or non-domain-specific facts are found and lead to a hallucination problem [3].”
BackgroundLauricella, S., & Edmunds, T. K. (2024) · Journal of Educational Informatics · doi:10.51357/jei.v4i2.227 · Cited by 2
Gómez, F. J. D., & Galende, J. N. (2024) · Revista Tecnología Ciencia y Educación · doi:10.51302/tce.2024.19081 · Cited by 7
“…se apoyara en otros supuestos (George y Stuhlmüller, 2023), o bien cuando, ante la falta de alineación factual, no pueden ser verificados a partir del contenido de una fuente (alucinaciones extrínsecas o de fidelidad) (Bruno et al. 2023; Guan et al. , 2023; Huang et al. , 2023; Ji et al. , 2023).”
BackgroundSridhar, A. K., Guo, Y., Visser, E., & Mahfuz, R. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448154 · Cited by 5
“Although there has been significant research in improving model performance, two major bottlenecks, hallucination [4] and large memory footprint[5], remain that inhibit the wide scale adoption of such tasks on constrained computing devices.”
BackgroundLee, J., & Jin, B. (2024) · Journal of Digital Contents Society · doi:10.9728/dcs.2024.25.3.823 · Cited by 2
12 Shades of RDF: Impact of Syntaxes on Data Extraction with Language Models
Ringwald, C., Gandon, F. L., Zucker, C. F., Michel, F., & Akl, H. A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78952-6_8 · Cited by 6
“This is a good starting point because LLM hallucination generally affects these literal values [8].”
BackgroundLDAS&ET-AD: Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation
Li, S., Hu, H., Yang, X., et al. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.047275 · Cited by 2
Improving Faithfulness and Factuality with Contrastive Learning in Explainable Recommendation
Zhuang, H., Zhang, W. E., Chen, W., Yang, J. Y., & Sheng, Q. Z. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3653984 · Cited by 7
Can a Large Language Model Generate Plausible Business Cases from Agent-Based Simulation Results?
Kikuchi, T., Tanaka, Y., Kunigami, M., Takahashi, H., & Terano, T. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-56388-1_11 · Cited by 3
Assessing ChatGPT Ability to Answer Frequently Asked Questions About Essential Tremor
Sorrentino, C., Canoro, V., Russo, M., Giordano, C., Barone, P., & Erro, R. (2024) · Tremor and Other Hyperkinetic Movements · doi:10.5334/tohm.917 · Cited by 3
“Moreover, there have been reports of a tendency of the model to occasionally “hallucinate”, that is to provide confidently formulated answers with incorrect or nonsensical content [39].”
BackgroundMentalistic Stances Towards AI Systems: Beyond the Intentional Stance
Larghi, S., & Datteri, E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66021-4_2 · Cited by 2
Adversarial Text Rewriting for Text-aware Recommender Systems
Oh, S., Verma, G., & Kumar, S. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679592 · Cited by 6
Benchmarking and Categorizing the Performance of Neural Program Repair Systems for Java
Zhong, W., Li, C., Liu, K., Ge, J., Luo, B., Bissyandé, T. F., & Ng, V. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3688834 · Cited by 5
CircuitVQA: A Visual Question Answering Dataset for Electrical Circuit Images
Mehta, R., Singh, B., Varma, V., & Gupta, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70341-6_26 · Cited by 14
CoURAGE: A Framework to Evaluate RAG Systems
Galla, D., Hoda, S., Zhang, M., Quan, W., Yang, T. D., & Voyles, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70242-6_37 · Cited by 4
Past Meets the Future—ChatGPT Integrated Pedagogy to Teach the 1947 Partition in Secondary Classes
Bisht, P., & Pujari, J. P. (2024) · Springer eBooks · doi:10.1007/978-3-031-65691-0_4 · Cited by 2
Personalized Product Description Generation With Gated Pointer-Generator Transformer
Liang, Y.-S., Chen, C.-Y., Li, C., & Chang, S. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3396840 · Cited by 3
“This issue has been extensively documented, with studies highlighting the challenges and proposing various solutions to mitigate the risk of hallucination in generated texts [8], [15], [34].”
Common errors in Generative AI systems used for knowledge extraction in the climate action domain
Havlik, D., & Pias, M. R. (2024) · Open Research Europe · doi:10.12688/openreseurope.17258.1 · Cited by 3
Using large language models to create narrative events
Bartalesi, V., Lenzi, E., & Martino, C. D. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2242 · Cited by 2
Cao, J. D., & Cao, J. (2024) · Electronics · doi:10.3390/electronics13214195 · Cited by 4
Combating Visual Question Answering Hallucinations via Robust Multi-Space Co-Debias Learning
Zhu, J., Liu, Y., Zhu, H., Lin, H., Jiang, Y., Zhang, Z., & Chen, B. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681663 · Cited by 12
Improving Factuality by Contrastive Decoding with Factual and Hallucination Prompts
Lv, B., Feng, A., & Xie, C. (2024) · Sensors · doi:10.3390/s24217097 · Cited by 5
Are You Sure About That: Eliciting Natural Language Confidence Indicators from Chatbots
Toney, A., & Singh, L. (2024) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3687272.3688318 · Cited by 4
Highlighting Case Studies in LLM Literature Review of Interdisciplinary System Science
McGinness, L. P., Baumgartner, P., Onyango, E., & Lema, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0348-0_3 · Cited by 8
“Hallucinations: It is well known that LLMs can ‘make up’ information [17].”
Graph-Based Grounding in a Conversational Clinical Decision Support System
Barham, S., Kelbaugh, M. T., Reddy, A., Ramsden, D., Chandler, C., Tobin-Williams, A., Elhadad, B. S., Cooper, G. R., & Alexander, K. (2024) · IEEE International Conference on Assured Autonomy (ICAA) · doi:10.1109/icaa64256.2024.00014 · Cited by 4
AI, Misinformation, and Fake News: A Literature Review of Ethical and Technical Approaches
AbuJarour, S., Qarariah, A., Saadeh, N. N., & Salem, M. (2024) · Contributions to finance and accounting · doi:10.1007/978-3-031-67547-8_55 · Cited by 7
Hamilton, Z., Aseem, A., Chen, Z., Naffakh, N., Reizine, N. M., Weinberg, F. D., Jain, S., Kessler, L. G., Gadi, V. K., Bun, C., et al. (2024) · JCO Clinical Cancer Informatics · doi:10.1200/cci.24.00123 · Cited by 9
“21,24 13-20, 25-28 25-28 When assessing the ability of”
Investigation of the Inference Capabilities and Memorization of Pre-trained Language Models
Sakai, Y., Kamigaito, H., Hayashi, K., & Watanabe, T. (2024) · Journal of Natural Language Processing · doi:10.5715/jnlp.31.1427 · Cited by 2
Kim, J.-H. (2024) · Journal of Musculoskeletal Science and Technology · doi:10.29273/jmst.2024.8.2.65 · Cited by 6
Medical Document Embedding Enhancement with Heterogeneous Mixture-of-Experts
Liu, X., Zhu, Y., Pang, T., Xue, K., Zhang, X., & Fan, C. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822374 · Cited by 6
“However, LLMs have limitations, particularly their tendency to generate plausible-sounding but factually incorrect information, a phenomenon commonly referred to as "hallucination" [11].”
Document Embeddings Enhance Biomedical Retrieval-Augmented Generation
Kong, Y., Yang, Z.-H., Luo, L., Ding, Z., Wang, L., Liu, W., Zhang, Y., Xu, B., Wang, J., Sun, Y.-Y., et al. (2024) · IEEE International Conference on Bioinformatics and Biomedicine · doi:10.1109/bibm62325.2024.10822781 · Cited by 2
Alleviating Action Hallucination for LLM-based Embodied Agents via Inner and Outer Alignment
Li, K., Zheng, Q., Zhan, Y., Zhang, C., Zhang, T., Lin, X., Qi, C., Li, L., & Tao, D. (2024) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai62207.2024.10826957 · Cited by 7
“In particular, LLM-based embodied agents may generate misleading action “hallucination”, fabricating erroneous or unfounded content [11].”
Understanding generative AI to harness its potentials and mini- mize risks: A perspective
Caselli, T. (2025) · European Journal of Radiology · doi:10.1016/j.ejrad.2025.111951 · Cited by 2
Following the Compass: LLM-Empowered Intent Translation with Manual Guidance
Guo, L., Wang, J., Wu, J., Yan, C., Sun, H., Zhuang, Z., Qi, Q., Dong, Y., Ren, H., & Liao, J. (2024) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp61940.2024.10858507 · Cited by 7
“Nonetheless, as black-box solutions, LLMs face challenges related to interpretability and security concerns [27], [28].”
A Review of Text Generation Based on Large Language Model
刘, 津. (2025) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2025.141019 · Cited by 2
Zhong, F., Luo, R., Napolitano, N. R., Tortora, C., Li, R., Zhu, X., Busillo, V., Koopmans, L. V. E., & Longo, G. (2025) · The Astrophysical Journal Supplement Series · doi:10.3847/1538-4365/ada609 · Cited by 6
“The flux 𝐹 𝑥 is normalized by the maximum flux within the input image’s 1 × 1arcsec center area as follows: To avoid fake outputs or “hallucinations” (Ji et al. 2023), which is important for scientific applications, we will use some ‘masks’ generated by U-Net.”
Towards Reflexive AI: A Comprehensive Exploration of Enhancing Social Science Research Through NLP
Shan, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-84460-7_49 · Cited by 7
Advanced Retrieval Augmented Generation for Local LLMs
Rocha, L. M., & Pessoa, R. M. (2024) · doi:10.5753/eniac.2024.245238 · Cited by 2
DialFill: Utilizing Dialogue Filling to Integrate Retrieved Knowledge in Responses
Xue, Q., Takiguchi, T., & Ariki, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3555650 · Cited by 2
“…they frequently produce hallucinations—responses that appear plausible but are The associate editor coordinating the review of this manuscript and approving it for publication was Fu Lee Wang . factually incorrect or irrelevant—due to the static and limited scope of their training data [5], [6].”
Zhao, J., Zhang, P., Wang, Y., Xin, R., Lu, X., Li, R., Lyu, S., Ou, Z., & Song, M. (2025) · Applied Sciences · doi:10.3390/app15073788 · Cited by 6
Rapp, S., Maedche, A., & Jainta, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88045-2_3 · Cited by 2
Li, H., Ren, Y., Cao, Y., Li, Y., Fang, F., Lin, Z., & Wang, S. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714571 · Cited by 3
Yin, Y., Mei, Y., Yu, C., Li, T. J.-J., Jadoon, A. K., Cheng, S., Shi, W., Chen, M., & Shi, Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713356 · Cited by 14
Multi-agent Chatbot for Efficient Interaction with Blockchain APIs
Nguyen, S.-H.-D., Trinh, T.-D., & Tran, Q.-V.-Q. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4288-5_33 · Cited by 2
Hsieh, P., & Lee, W. (2025) · Expert Systems · doi:10.1111/exsy.70049 · Cited by 3
The Jury is in: An Evaluation of an Experiential Court Assignment
Bullock, J., & Sparks, B. (2025) · Journal of Criminal Justice Education · doi:10.1080/10511253.2025.2500316 · Cited by 4
FaceOracle: Chat with a Face Image Oracle
Kabbani, W., Raja, K. B., Ramachandra, R., & Busch, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92089-9_14 · Cited by 3
Advancing AI Incidents Classification: Leveraging LLMs with Strategic Prompting
Chen, Y., Do, L., Yi, L., Baeza-Yates, R. A., & Guerra‐Gomez, J. A. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-91328-0_4 · Cited by 2
Kastor: Fine-Tuned Small Language Models for Shape-Based Active Relation Extraction
Ringwald, C., Gandon, F. L., Zucker, C. F., Michel, F., & Akl, H. A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-94575-5_6 · Cited by 3
“A first dichotomy is proposed in [13] between the intrinsic hallucination (which contradicts the input) and the extrinsic hallucination (which cannot be verified by the input).”
Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering
Jiang, L., Huang, J., Möller, C., & Usbeck, R. (2025) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc64641.2025.00010 · Cited by 12
“LLMs suffer from issues such as hallucination [16] and factual inaccuracy when answering questions, mainly because they lack domain-specific knowledge, stemming from insufficient training data or missing interactions with an unseen or heterogeneous KG [17].”
Mindlin, D., & Cimiano, P. (2025) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc64641.2025.00015 · Cited by 3
“A major concern is the risk of LLM hallucinations [20], which can produce inaccurate explanations, causing misunderstandings and undermining their benefits.”
Balderas-Martínez, Y. I., Sánchez-Rojas, J. A., Téllez‐Velázquez, A., Martínez, F. J., Cruz‐Barbosa, R., Guzmán‐Ramírez, E., García, I., & Arroyo‐Fernández, I. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9060162 · Cited by 3
Kim, A., Sachdeva, A., & Dennis, A. R. (2025) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2025.102938 · Cited by 13
Sufi, F. K., & Alsulami, M. (2025) · Mathematics · doi:10.3390/math13132049 · Cited by 9
Chatgpt Inaccuracy Mitigation During Technical Report Understanding: Are we There Yet?
Tamanna, S. B., Uddin, G., Wang, S., Xia, L., & Zhang, L. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00145 · Cited by 6
He, T., Stanković, A., Niforatos, E., & Kortuem, G. (2025) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3719160.3736633 · Cited by 6
Learning in the Age of LLMs: Boosting not Bypassing the Learning Process
Blake, J. (2025) · Educational communications and technology yearbook · doi:10.1007/978-981-96-2921-3_9 · Cited by 4
Burton‐Jones, A., Amano, T., Boyce, J. F., Chau, P. Y. K., Feng, J., Guzman, I. R., Järvenpää, S. L., Li, J. (., Namvar, M., Padmanabhan, B., et al. (2025) · AJIS. Australasian journal of information systems/AJIS. Australian journal of information systems/Australian journal of information systems · doi:10.3127/ajis.v29.5875 · Cited by 3
Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware
Chen, Y., Chen, M., Gao, C., Jiang, Z., Li, Z., & Ma, Y. (2025) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3696630.3728569 · Cited by 18
KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
Li, R. L., Dai, Q., Zhang, Z., Chen, X., Dong, Z., & Wen, J.-R. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737015 · Cited by 21
Generating Authentic Grounded Synthetic Maintenance Work Orders
Lau, A., Feng, J., Hodkiewicz, M. R., Woods, C., Stewart, M. G., & Polpo, A. (2025) · IEEE Access · doi:10.1109/access.2025.3598751 · Cited by 4
“Controlling this situation is particularly challenging when using LLMs due to their tendency to hallucinate and generate content that lacks factual accuracy and consistency with real-world knowledge or is extraneous to what is being asked for [19], [20], [21].”
Kumar, A., Gupta, P., & Pandey, A. K. (2025) · Indian Journal of Critical Care Medicine · doi:10.5005/jp-journals-10071-25027 · Cited by 2
Hallucination Detection on Code Generation with SelfCheckGPT
Ito, W., Obara, Y., Sato, M., & Kuramitsu, K. (2025) · Journal of Information Processing · doi:10.2197/ipsjjip.33.487 · Cited by 5
MultiTalk: Introspective and Extrospective Dialogue for Human-Environment-LLM Alignment
Devarakonda, V. N., Kaypak, A. U., Yuan, S., Krishnamurthy, P., Fang, Y., & Khorrami, F. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128486 · Cited by 3
“However, initial attempts lacked accuracy due to LLMs’ hallucinations ([10]–[13]), which resulted in incorrect plans.”
Large Language Models in Neurology Treatment Decision-Making: a Scoping Review
Shah, R., & Jotterand, F. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02254-4 · Cited by 2
Pathology Report Generation and Multimodal Representation Learning for Cutaneous Melanocytic Lesions
Lucassen, R. T., Moonemans, S. P. J., van de Luijtgaarden, T., Breimer, G. E., Blokx, W. A. M., & Veta, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04978-0_48 · Cited by 8
Trust or distrust? AIGC trustworthiness and an extended analysis within nomology framework
Li, M., Du, R., Ai, S., Hunt, R. A., & Xie, J. (2025) · Data Science and Management · doi:10.1016/j.dsm.2025.09.005 · Cited by 4
Lü, W., Peng, X., Huang, Y., Zheng, Z., Zhu, Z., Yin, X., Xu, W., Mei, S., Lu, X., Zhang, X., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01955 · Cited by 3
Null Space Properties of Neural Networks with Applications to Image Steganography
Li, X., & Short, K. M. (2025) · Mathematics · doi:10.3390/math13213394 · Cited by 3
HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs
Dasgupta, S., Nath, S., Basu, A., Shamsolmoali, P., & Das, S. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228484 · Cited by 18
“Recent studies have explored various approaches to detect and mitigate hallucinations in natural language generation tasks [3], [24].”
Retrieval-Augmented Multi-Modal Chain-of-Thoughts Reasoning for Large Language Models
Liu, B., Lyu, C., Min, Z., Wang, Z., Su, J., & Wang, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228391 · Cited by 39
Mittal, A., Tadi, G., & Madduri, S. (2025) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon67449.2025.11267527 · Cited by 3
“Building upon foundational work by Ji et al. [1] and Rawte et al. [2], we present a comprehensive taxonomy: Factuality Hallucinations: Discrepancies be-tween generated content and verifiable facts, including entity-level errors (object existence, incorrect names), relation-level errors (incorrect…”
Clean up the mess: Addressing data pollution in cryptocurrency abuse reporting services
Gómez, G., van Liebergen, K., Sanvito, D., Siracusano, G., Gonzalez, R., & Caballero, J. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108313 · Cited by 7
“The prompt instructs the LLM to take the role of a cybersecurity expert and avoid assuming facts not in the description to minimize hallucinations [44].”
Scaria, N., Kennedy, S. J. J., Latinovich, T., & Subramani, D. (2025) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2025.100539 · Cited by 8
Lu, R., Shen, J., Jiang, A., Chen, W., Qi, C., Chen, L., Zhu, L., Mou, W., Gan, W., Zeng, D., et al. (2025) · Interdisciplinary medicine · doi:10.1002/inmd.70047 · Cited by 6
Knoll: Creating a Knowledge Ecosystem for Large Language Models
Zhao, D., Yang, D., & Bernstein, M. S. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747711 · Cited by 11
Architecting Trustworthy LLMs: A Unified TRUST Framework for Mitigating AI Hallucination
Meng, L. (2025) · Journal of Computer Science and Frontier Technologies · doi:10.63313/jcsft.9019 · Cited by 51
LLMs prompted for graphs: hallucinations and generative capabilities
Richardeau, G., Chali, S., Merrer, E. L., Penzo, C., & Trédan, G. (2025) · Applied Network Science · doi:10.1007/s41109-025-00754-3 · Cited by 8
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.




