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 1,401–1,500 of 4,844
Alshamy, A. S., Al-Harthi, A. S. A., & Abdullah, S. (2025) · 2025 International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets65254.2025.11106833 · Cited by 5
“Another challenge is that GenAI tools are prone to hallucinate, producing content that is factually incorrect or inconsistent or generating incorrect citations and referencing, which can mislead users and degrade the quality of academic work for both academics and students [24, 25].”
Algorithmic bias, generalist models, and clinical medicine
Keeling, G. (2024) · AI and Ethics · doi:10.1007/s43681-023-00329-x · Cited by 5
“A related issue is that language models may be more likely to hallucinate false information in domains of discourse that are underrep-resented in the training data (Ji et al., 2023).”
A conversational agent for enhanced Self-Management after cardiothoracic surgery
Martins, A., Lapão, L. V., Nunes, I. L., Giordano, A. P., Semedo, H., Vital, C., da Silva, R. A., Coelho, P., & Londral, A. R. M. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105640 · Cited by 7
Vision-Based Hand Gesture Customization from a Single Demonstration
Shahi, S., Mollyn, V., Park, C. T., Kang, R., Liberman, A., Levy, O., Gong, J., Bedri, A., & Laput, G. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676378 · Cited by 16
Evaluation of Multilingual Simplifications of IR Procedural Reports Using GPT-4
Li, H., Moon, J. T., Kumar, S., Ricci, J., Sim, N., Bercu, Z. L., Newsome, J. M., Trivedi, H., & Gichoya, J. W. (2025) · Journal of Vascular and Interventional Radiology · doi:10.1016/j.jvir.2025.01.002 · Cited by 8
Fact or Fiction? Exploring Explanations to Identify Factual Confabulations in RAG-Based LLM Systems
Reinhard, P., Li, M. M., Fina, M., & Leimeister, J. M. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720249 · Cited by 13
Yang, Y., Tan, Y., Lin, Y. C., King, J., Liu, Z., & Lee, Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713770 · Cited by 13
Toward Affective Empathy via Personalized Analogy Generation: A Case Study on Microaggression
Ju, H., Lee, J., Yang, S., Ok, J., & Hwang, I. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714122 · Cited by 16
Visual hallucination detection in large vision-language models via evidential conflict
Huang, T., Liu, Z., Wang, R., Zhang, Y., & Jing, L. (2025) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2025.109507 · Cited by 18
Judson, H. (2025) · Teaching Sociology · doi:10.1177/0092055x251342530 · Cited by 10
“…which this leads to significant limitations for text-based genAI models, particularly in hallu-cinating information and biases in the training data (Ji et al. 2023), and that identifying false information and hallucinations from genAI texts requires a depth of subject mastery that they as students…”
Chen, Y., Dong, M., Sun, J., Meng, Z., Yang, Y., Muhetaier, A., Li, C., & Qin, J. (2025) · JMIR Medical Informatics · doi:10.2196/70967 · Cited by 6
“First, the model’s inherent hallucinations [32] may cause misleading outputs during the reasoning process of structured data.”
Misinformation and Disinformation in Generative AI—A Survey
Srinivasan, R. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8183-9_23 · Cited by 5
Generative artificial intelligence policies: information governance
Wang, X., Liu, B., & Bao, L. (2025) · Management Decision · doi:10.1108/md-06-2024-1422 · Cited by 7
Lee, S., Lee, H., Lee, H., Yum, K. S., Baek, J., Khil, J., Lee, J. Y., Shin, S., Cho, M., Ahn, N. Y., et al. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf099 · Cited by 4
Exposing the Ideology of Large Language Models with Creative Practices
Cremaschi, M., Grigis, P., Dorfmann, M., & Angeli, A. D. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735715 · Cited by 8
Tao, D., Wang, C., Huang, F., Chen, J., Huang, Y., & Jiang, M. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114011 · Cited by 13
Li, T. W., Song, Y., Sundaram, H., & Karahalios, K. G. (2025) · ACM Conference on Learning @ Scale (L@S) · doi:10.1145/3698205.3729550 · Cited by 7
El‐Bassel, N., David, J., Mukherjee, T. I., Aggarwal, M., Wu, E., Gilbert, L., Walters, S. T., Chandler, R. K., Hunt, T., Frye, V. A., et al. (2025) · Implementation Science · doi:10.1186/s13012-025-01447-2 · Cited by 11
“RAG methods, paired with human review, are recommended to reduce hallucinations in tasks such as transcript summarization [63, 64].”
Generating Planning Feedback for Open-Ended Programming Exercises with LLMs
Demirtaş, M. A., Zheng, C., Fowler, M., & Cunningham, K. I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98417-4_3 · Cited by 11
C-PATH: Conversational Patient Assistance and Triage in Healthcare System
Shi, Q. F., Han, Q., & Soares, C. (2025) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh67620.2025.00016 · Cited by 7
“Furthermore, hallucination remains a concern in patient-facing contexts, especially when models confidently present incorrect information due to training artifacts [12].”
ZeroED: Hybrid Zero-Shot Error Detection Through Large Language Model Reasoning
Ni, W., Zhang, K., Miao, X., Zhao, X., Wu, Y., Wang, Y., & Yin, J. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00234 · Cited by 20
“The emergence of LLMs such as ChatGPT [57], [58], Llama [52], [59], and Qwen [51], [60], has revolutionized current applications, demonstrating impressive capabilities in in-context learning [20], [61]–[63], adherence to instructions [64]–[66], and chain-of-thought reasoning [67]–[69].”
“It Becomes Very Intelligent”: ChatGPT as an Academic Reading Tool for Postgraduates
Abdullah, A. D., Qiu, X., Li, H., & Kabilan, M. K. (2025) · Reading Research Quarterly · doi:10.1002/rrq.70058 · Cited by 12
A Novel Approach to Mimic Linguistic Features of Transcripts of Atypical Speech
Mirbagheri, M., Saghir, H., & Chau, T. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3603921 · Cited by 6
“The lackofparalleldatapresentsamajorchallengefordeeplearning methods,evenadvancedmodelsliketheT5[31];itisdifficult formodelstoconstraingenerationbytransferringonlyspecific linguisticfeatures[32],[33].”
Sivathanu, B., Pillai, R., & Rana, N. P. (2025) · Journal of Computer Information Systems · doi:10.1080/08874417.2025.2554850 · Cited by 11
Robust Neural Information Retrieval: An Adversarial and Out-of-Distribution Perspective
Liu, Y.-A., Zhang, R., Guo, J., de Rijke, M., Fan, Y., & Cheng, X. (2025) · ACM Transactions on Information Systems · doi:10.1145/3768153 · Cited by 40
Red Reading The Text: On How To Red Team Texts Using LLMs
Floridi, L., Morley, J., & Novelli, C. (2025) · Philosophy & Technology · doi:10.1007/s13347-025-00955-9 · Cited by 7
“This includes the well-documented phenomenon of “hallucinations”, where LLMs confidently present fabricated information as fact (Huang et al., 2023, Ji et al. 2023).”
Riegler, M. A., Hellton, K. H., Thambawita, V. L., & Hammer, H. L. (2025) · Scientific Reports · doi:10.1038/s41598-025-18425-9 · Cited by 17
“This can lead to outputs that are inconsistent, biased, or factually incorrect–a phenomenon often termed “hallucination” 7 .”
Park, J., Lee, J. H., Yoon, M. A., Kim, D. H., Jung, J., & Lee, Y. H. (2025) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2025.0018 · Cited by 8
“This tendency to present inaccurate information as truth is one of the most frequently cited and potentially consequential pitfalls of LLMs, raising serious concerns about their reliability in high-stakes medical contexts (58, 59).”
Liu, Z., Kou, J., Zhang, W., Gu, C., Fang, X., Huang, Z., Hao, Y., Li, H., Lu, X., Yin, A., et al. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189137 · Cited by 12
UAV Accident Forensics via HFACS-LLM Reasoning: Low-Altitude Safety Insights
Yan, Y., Li, B., & Lodewijks, G. (2025) · Drones · doi:10.3390/drones9100704 · Cited by 11
“The application of LLMs to complex reasoning tasks has revealed a fundamental tension between generative capabilities and propensity for hallucination in specialized domains [51].”
DefAn: Definitive Answer Dataset for LLM Hallucination Evaluation
Rahman, A., Anwar, S., Usman, M., Ahmad, I., & Mian, A. S. (2025) · Information · doi:10.3390/info16110937 · Cited by 24
“Hallucination is defined as the LLM-generated response that lacks coherence or deviates from the original source material [6,7].”
Tavares, V. (2025) · Pedagogy Culture and Society · doi:10.1080/14681366.2025.2585887 · Cited by 8
“…I rely on converging evidence that current text-only models are not sensorimotorly grounded (Bisk et al. 2020), show non-trivial rates of unverifiable or fabricated claims in openended generation (Ji et al. 2023), and obscure provenance through opaque training data (Birhane and Prabhu 2021).”
Huynh, L., & McNamara, D. S. (2025) · Applied Sciences · doi:10.3390/app152212128 · Cited by 13
Pratte, M., Thirukumar, S., Zhang, C., Slessarev, M., Basmaji, J., & Prager, R. (2026) · Journal of Critical Care · doi:10.1016/j.jcrc.2025.155358 · Cited by 7
Zheng, C., & Chen, G. (2025) · International Journal of Chinese Education · doi:10.1177/2212585x251400819 · Cited by 11
“Hallucinations and Factual Errors: Large language models occasionally generate plausible-sounding but factually incorrect information, a phenomenon termed ‘ hallucinations ’ (Ji et al., 2023).”
Khapre, S., Mersha, M. A., Shakil, H., Baruah, J., & Kalita, J. K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129832 · Cited by 15
“Hallucination in generative AI refers to the phenomenon where models generate incorrect, misleading, or fabricated content, often presented as factual information [146, 135].”
Understanding Programming Students' Help-Seeking Preferences in the Era of Generative AI
Penney, J., Acharya, P., Hilbert, P., Parekh, P., Sarma, A., Steinmacher, I., & Gerosa, M. A. (2025) · ACM Global Computing Education Conference (CompEd) · doi:10.1145/3736181.3747165 · Cited by 11
Accelerating Retrieval Augmented Language Model via PIM and PNM Integration
Jang, J.-W., Oh, J., Kong, Y., Hong, J.-Y., Cho, S.-H., Lee, J., Yang, H., & Yang, J.-S. (2025) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3725843.3756020 · Cited by 9
VLM-MPC: Model predictive controller augmented vision language model for autonomous driving
Long, K., Shi, H., Liu, J., Xiao, C., & Li, X. S. (2025) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2025.105487 · Cited by 44
Liu, Z., Hu, B., Feng, Y., Lu, C., & Tan, J. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104264 · Cited by 11
Liu, C., & Lin, C. (2026) · Online Information Review · doi:10.1108/oir-04-2025-0233 · Cited by 13
Hu, H., Wang, L., Chen, L., Lin, H., Huang, L.-T., Wang, Z.-W., & Hou, X. (2026) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.5c03511 · Cited by 5
A survey of large language models for legal tasks: Progress, prospects and challenges
He, C., Hu, H., Li, Y., Zhang, H., & Zhang, Q. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100906 · Cited by 16
Miftaroski, A., Zowalla, R., Wiesner, M., & Pobiruchin, M. (2026) · JMIR AI · doi:10.2196/77149 · Cited by 9
“It is well known that LLMs tend to hallucinate [36,64] or “escalate the minor biases that could occur in the data bank with which it gets trained” [35].”
Beyond Search: Measuring LLM Performance for Scientific Literature Discovery
Hang, C. N., Yu, P.-D., Tan, C. W., & Chiu, D. M. (2025) · IEEE International Conference on Teaching, Assessment, and Learning for Engineering · doi:10.1109/tale66047.2025.11346619 · Cited by 10
“On the other hand, LLMs are known to generate plausible-sounding but incorrect information, a phenomenon known as “hallucination” [11]–[14].”
Castagnone, A., & Nitti, G. (2026) · Buildings · doi:10.3390/buildings16030534 · Cited by 7
Li, L., Wang, T., Wang, Y., Wang, Y., & Zeng, X. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2618563 · Cited by 10
“Moreover, given CAI’s inherent limitations (e.g., hallucinations, factual inaccuracies) (Ji et al., 2023; Krause et al., 2023), verifying its outputs often requires additional cognitive effort.”
General-Purpose Models for the Chemical Sciences: LLMs and Beyond
Alampara, N., Aneesh, A., Ríos-García, M., Mirza, A., Schilling-Wilhelmi, M., Aghajani, A. A., Sun, M., Prastalo, G., & Jablonka, K. M. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.5c00583 · Cited by 37
The Apt Curation Model: An Epistemic Virtue Theory of AI-Assisted Authorship
Rodrigues, T. V. (2026) · Philosophy & Technology · doi:10.1007/s13347-026-01038-z · Cited by 15
“AI systems lack expert competence, and they cannot provide truthful information while their reliability performance remains unstable because they generate confident false statements (“ hallucinations ”) without logical basis (Ji et al., 2023).”
Mirhosseini, N., Shojaei, D., & Sabri, S. (2026) · Building Research & Information · doi:10.1080/09613218.2026.2637965 · Cited by 13
Mohammed, U. A. (2026) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds69358.2026.11540135 · Cited by 5
“This is essential in enterprise analytics, where schema grounding is needed to ensure correctness of column names, types, keys, units, business definitions, and constraints; otherwise, in models, hallucinations can occur, which is expensive in both operational and compliance environments [3], [4].”
Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model
Jia, Q., Ren, S., Liu, Y., & Zhu, K. Q. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.679 · Cited by 36
SumBlogger: Abstractive Summarization of Large Collections of Scientific Articles
Zakkas, P., Verberne, S., & Zavrel, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56027-9_23 · Cited by 16
Tri-Modal Transformers With Mixture-of-Modality-Experts for Social Media Prediction
Chen, W., Hu, W., Chen, X., Yuan, W., Wang, Y., Zhang, Y., & Han, Z. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3474101 · Cited by 8
“The performance of LLM on natural language generation tasks (NLG) [60] data and ensure the semantics of the original data while using new data.”
Mao, Q., Li, J., Zhou, H., Kar, P., & Bellotti, A. G. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128897 · Cited by 6
Exploring diabetes through the lens of AI and computer vision: Methods and future prospects
Chundi, R., Gomathy, S., Basivi, P. K., Tippana, A., Hulipalled, V. R., Prabakaran, N., Simha, J. B., Kim, C. W., Kakani, V., & Pasupuleti, V. R. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109537 · Cited by 9
A discrete convolutional network for entity relation extraction
Yang, W., Qin, Y., Wang, K., Hu, Y., Huang, R., & Chen, Y. (2025) · Neural Networks · doi:10.1016/j.neunet.2024.107117 · Cited by 8
Hakdağlı, Ö. (2024) · Orclever Proceedings of Research and Development · doi:10.56038/oprd.v5i1.535 · Cited by 5
Evaluating Class Membership Relations in Knowledge Graphs Using Large Language Models
Allen, B. P., & Groth, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78952-6_2 · Cited by 13
“…include using temperature sampling [1] for self-consistency [35] and uncertainty estimation [21], mitigating hallucination in rationale generation [22], and addressing faithfulness in rationale generation [33,2] are three other areas for future work, in addition to work on addressing the…”
BackgroundGenerative AI Decision-Making Attributes in Complex Health Services: A Rapid Review
Doreswamy, N., & Horstmanshof, L. (2025) · Cureus · doi:10.7759/cureus.78257 · Cited by 11
Li, C., Xing, B., Huo, D., Zhou, Q., Xu, Z., & Wang, Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889328 · Cited by 6
“Their work revealed that comparing the impact of context embeddings from different layers on the output shows that the probability of the last token in the final layer’s context embedding is effective in identifying hallucinations [13].”
Requirements for a Digital Library System: A Case Study in Digital Humanities
Kroll, H., Kreutz, C. K., Jehn, M., & Risse, T. (2024) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3677389.3702502 · Cited by 10
Conversational Explanations: Discussing Explainable AI with Non-AI Experts
Zhang, T., Zhang, M., Low, W. Y., Yang, X. J., & Li, B. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712143 · Cited by 18
Zhang, L., Song, Y., Cui, H., Lu, M., Li, C., Yuan, B., Wang, B., Lall, U., & Yang, J. (2025) · Water Resources Research · doi:10.1029/2024wr039553 · Cited by 14
“This issue could arise from discrepancies in the referenced data or the transformer architecture's tendency to predict the most statistically likely next word in a sequence rather than ensuring factual accuracy (Holtzman et al., 2020; Ji et al., 2023).”
WebGLM: Towards an Efficient and Reliable Web-Enhanced Question-Answering System
Lai, H., Liu, X., Yu, H., Xu, Y., Iong, I. L., Yao, S., Zeng, A., Du, Z., Dong, Y., & Tang, J. (2025) · ACM Transactions on Information Systems · doi:10.1145/3729421 · Cited by 12
Self-citationLee, W.-Y., Han, S. Y., Kim, J.-H., Lee, B.-W., Han, Y., & Lee, S.-H. (2025) · Applied Sciences · doi:10.3390/app15094862 · Cited by 7
LLM-empowered literature mining for material substitution studies in sustainable concrete
Duan, Y., Tian, Y., Ghosh, S., Venugopal, V., Chen, J., & Olivetti, E. (2025) · Resources Conservation and Recycling · doi:10.1016/j.resconrec.2025.108379 · Cited by 10
AI-Empowered Genome Decoding: Applications of Large Language Models in Genomics
Li, S., Fan, W., & Zhou, Y. (2025) · Frontiers of digital education. · doi:10.1007/s44366-025-0051-1 · Cited by 4
Huynh, L., & McNamara, D. S. (2025) · Applied Sciences · doi:10.3390/app15126791 · Cited by 14
CIRAG: Retrieval-Augmented Language Model with Collective Intelligence
Cui, C., Fan, H., Zhang, J., Shen, L., Li, B., & Wang, W. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3729921 · Cited by 8
IOAgent: Democratizing Trustworthy HPC I/O Performance Diagnosis Capability via LLMs
Egersdoerfer, C., Sareen, A., Bez, J. L., Byna, S., Xu, D., & Dai, D. (2025) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps64566.2025.00036 · Cited by 12
“Third, LLMs are known to produce hallucinations, plausible but factually incorrect or non-sensical outputs, which are unacceptable for use as a diagnosis tool by domain scientists [18].”
Towards Reliable Large Language Models: A Survey on Hallucination Detection
Pan, Y., Kong, L., Wu, J., Yang, Y., Zuo, H., Xiu, Z., & Wang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0014-7_37 · Cited by 10
Barriers and enabling factors for error analysis in NLG research
van Miltenburg, E., Clinciu, M., Dušek, O., Gkatzia, D., Inglis, S., Leppänen, L., Mahamood, S., Schoch, S., Thomson, C., & Wen, L. (2023) · Northern European Journal of Language Technology · doi:10.3384/nejlt.2000-1533.2023.4529 · Cited by 15
A Survey of Recent Error Annotation Schemes for Automatically Generated Text
Huidrom, R., & Belz, A. (2022) · Workshop on Generation, Evaluation and Metrics (GEM) · doi:10.18653/v1/2022.gem-1.33 · Cited by 6
Maclean, K. D. S., & Bayley, T. (2023) · INFORMS Transactions on Education · doi:10.1287/ited.2023.0020 · Cited by 7
Liu, X., & Sajda, P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43075-6_39 · Cited by 5
Fecho, K., Bizon, C., Issabekova, T., et al. (2023) · Journal of Clinical and Translational Science · doi:10.1017/cts.2023.619 · Cited by 5
“Moreover, Translator does not “ hallucinate ” [37] or fabricate knowledge or assertions; rather, it invokes reasoning algorithms to expose curated knowledge or draw inferences, supported by complete evidence, provenance, and confidence.”
BackgroundDetermining epitope specificity of T-cell receptors with transformers
Khan, A. R., Reinders, M. J. T., & Khatri, I. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad632 · Cited by 5
FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation
Zhang, K., Balalau, O., & Manolescu, I. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.672 · Cited by 14
Becoming a Knower: Fabricating Knowing Through Coaction
Fester-Seeger, M.-T. (2023) · Social Epistemology · doi:10.1080/02691728.2023.2266716 · Cited by 5
Legally Enforceable Hate Speech Detection for Public Forums
Luo, C., Bhambhoria, R. V., Dahan, S., & Zhu, X. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.730 · Cited by 16
Mitigating Intrinsic Named Entity-Related Hallucinations of Abstractive Text Summarization
Shen, J., Xuan, J., & Liang, C. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.1059 · Cited by 11
RefGPT: Dialogue Generation of GPT, by GPT, and for GPT
Yang, D., Yuan, R., Fan, Y., Yang, Y., Wang, Z., Wang, S., & Zhao, H. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.165 · Cited by 41
What Else Do I Need to Know? The Effect of Background Information on Users’ Reliance on QA Systems
Goyal, N., Briakou, E., Liu, A., Baumler, C., Bonial, C., Micher, J. C., Voss, C. R., Carpuat, M. J., & Daumé, H. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.201 · Cited by 19
Questions about Contracts: Prompt Templates for Structured Answer Generation
Roegiest, A., Chitta, R., Donnelly, J., Lash, M., Vtyurina, A., & Longtin, F. (2023) · Natural Legal Language Processing Workshop (NLLP) · doi:10.18653/v1/2023.nllp-1.8 · Cited by 16
Learning to Supervise Knowledge Retrieval Over a Tree Structure for Visual Question Answering
Xu, N., Lu, Z., Tian, H., Kang, R., Cao, J., Zhang, Y., & Liu, A.-A. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3355638 · Cited by 12
“As widely known, some large-scale language models may encounter the issue of “hallucinations”, whereby the generated text seems correct but reveals a range of inaccuracies from minor examination [43].”
BackgroundGPT-in-the-Loop: Supporting Adaptation in Multiagent Systems
do Nascimento, N. M., Alencar, P., & Cowan, D. D. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386490 · Cited by 26
“Furthermore, GPT models, including GPT-4, are sometimes prone to ‘hallucinations’ – instances where they produce responses that are not just contextually irrelevant but also factually incorrect or disconnected from reality [26].”
BackgroundTraining AI Model that Suggests Python Code from Student Requests in Natural Language
Kuramitsu, K., Obara, M., Sato, M., & Akinobu, Y. (2024) · Journal of Information Processing · doi:10.2197/ipsjjip.32.69 · Cited by 8
Standardized nomenclature for litigational legal prompting in generative language models
Sivakumar, A., Gelman, B. U., Simmons, R. A., et al. (2024) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00108-5 · Cited by 5
Building Confidence in a World of Eroding Trust
Lim, J. W. Z., & Thing, V. L. L. (2024) · Digital Government Research and Practice · doi:10.1145/3653075 · Cited by 8
Response Enhanced Semi-supervised Dialogue Query Generation
Huang, J., Wang, A., Gao, L., Song, L., & Su, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29790 · Cited by 9
What Is Generative in Generative Artificial Intelligence? A Design-Based Perspective
Bordas, A., Masson, P. L., Thomas, M., & Weil, B. (2024) · Springer eBooks · doi:10.1007/978-3-031-71922-6_8 · Cited by 7
Fayyaz, Y., Almehmadi, A., & El‐Khatib, K. (2024) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2024.301751 · Cited by 12
Salfinger, A., & Snidaro, L. (2024) · IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) · doi:10.1109/cogsima61085.2024.10553903 · Cited by 7
“…to safe-guard against the known inherent deficiencies of LLMs: i) LLMs occasionally generate factually wrong information, known as hallucinations [9], a problem rooted in their training task on predicting the most likely next word, which thus only trains them in generating plausibly sounding…”
BackgroundKnowledge-based Word Tokenization System for Urdu
Khan, W., Khan, A., Khan, K., Khan, S. N., & Haq, R. (2024) · Journal of Informatics and Web Engineering · doi:10.33093/jiwe.2024.3.2.6 · Cited by 12
Towards AI for Software Systems
Eskandani, N., & Salvaneschi, G. (2024) · ACM International Conference on AI-Powered Software (AIware) · doi:10.1145/3664646.3664767 · Cited by 7
Manufacturing Domain QA with Integrated Term Enhanced RAG
Bei, Y., Fang, Z., Mao, S., Yu, S., Jiang, Y., Tong, Y., & Cai, W. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10649905 · Cited by 11
“However, their effectiveness in specialized domains is often hampered by challenges such as model hallucination and the lack of in-depth domain-specific knowledge [3], [4], [33].”
BackgroundMitigating Hallucination Issues in Small-Parameter LLMs through Inter-Layer Contrastive Decoding
Li, F., zhang, X., & Zhang, P. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650644 · Cited by 5
“The hallucination issue refers to generating content that deviates from real-world facts observed during pre-training [4].”
BackgroundInfluentialDouble Attention: An Optimization Method for the Self-Attention Mechanism Based on Human Attention
Zhang, Z., Li, B., Yan, C., Furuichi, K., & Todo, Y. (2025) · Biomimetics · doi:10.3390/biomimetics10010034 · Cited by 7
Li, J., Yuan, R., Tian, Y., & Li, J. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822624 · Cited by 6
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.




