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 2,101–2,200 of 4,843
When AI Gets It Wrong: Scaffolding AI Hallucination Detection for Children Through Chatbot Creation
Tian, X., Ozturk, D., Edula, S., Adil, J., Jin, Q., Shi, Y., & Barnes, T. M. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791480 · Cited by 10
SceneScout: Towards AI-Driven Access to Street Level Imagery for Blind Users
Jain, G., Findlater, L., & Gleason, C. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790449 · Cited by 14
Yeo, H., Jin, S., Noh, T., Shin, Y., Kang, S., Heo, S., Chung, J., Hyun, H., & Han, K. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791188 · Cited by 7
Characterizing User-Reported Risks across LLM Chatbots
Li, L., Ma, R., Xue, Z., & Xiong, J. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791505 · Cited by 3
Characterizing Unintended Consequences of GUI Agents For Web Browsing
Zhang, S., Chen, J., Gao, Z., Gao, J., Yi, X., & Li, H. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790696 · Cited by 19
Artificial Intelligence and the Journal of Clinical Psychopharmacology
Rothschild, A. J. (2023) · Journal of Clinical Psychopharmacology · doi:10.1097/jcp.0000000000001752 · Cited by 2
On Evaluating Multilingual Compositional Generalization with Translated Datasets
Wang, Z., & Hershcovich, D. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.93 · Cited by 9
The current state of summarization
Retkowski, F. (2023) · AI critique · doi:10.1515/9783839467664-016 · Cited by 11
Guided Beam Search to Improve Generalization in Low-Resource Data-to-Text Generation
Garneau, N., & Lamontagne, L. (2023) · International Conference on Natural Language Generation · doi:10.18653/v1/2023.inlg-main.1 · Cited by 4
“Hence, generations can also be evaluated based on the number of hallucinated facts produced by the model (Dušek et al., 2018; Ji et al., 2022).”
BackgroundKobza, O., Herel, D., Čuhel, J., Gargiani, T., Pichl, J., Marek, P., Konrád, J., & Sedivy, J. (2023) · Future Internet · doi:10.3390/fi15120384 · Cited by 2
Liu, K., Casper, S., Hadfield-Menell, D., & Andreas, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.291 · Cited by 80
ChatGPT Guided Diagnosis of Ameloblastic Fibro-Odontoma: A Case Report with Eventful Healing
Uranbey, Ö., Ayrancı, F., & Erdem, B. E. (2024) · European Journal of Therapeutics · doi:10.58600/eurjther1979 · Cited by 2
For any disease a human can imagine, ChatGPT can generate a fake report
Yokokawa, D., Yanagita, Y., Li, Y., Yamashita, S., Shikino, K., Noda, K., Tsukamoto, T., Uehara, T., & Ikusaka, M. (2024) · Diagnosis · doi:10.1515/dx-2024-0007 · Cited by 2
Navigating Uncertainty: Optimizing API Dependency for Hallucination Reduction in Closed-Book QA
Erbacher, P., Falissard, L., Guigue, V., & Soulier, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56063-7_31 · Cited by 5
Playing the Imitation Game: Human-AI Simulators in Pedagogic Design
Armaselu, F. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia240181 · Cited by 2
“While optimistic areas of human activity, which may not always have predictable or positive outcomes [5,6].”
BackgroundChatGPT and Large Language Models (LLMs) in Healthcare: Opportunities and RisksPreprint
Ali, H., Qadir, J., Alam, T., Househ, M. S., & Shah, Z. (2023) · doi:10.36227/techrxiv.22579852 · Cited by 5
Gpt-3.5 Hallucinates Nonexistent Citations: Evidence from EconomicsPreprint
Buchanan, J. A., & Shapoval, O. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4472220 · Cited by 3
Editorial 2024: Large language models, artificial intelligence and geomorphology
Lane, S. N. (2024) · Earth Surface Processes and Landforms · doi:10.1002/esp.5773 · Cited by 3
“In the most extreme case, the LLMs ‘ hallucinate ’ in which the generated text may make no sense or may be wrong; but it is presented in such a convincing argument that it can be interpreted as correct (Ji et al., 2023).”
BackgroundWysocka, M., Wysocki, O., Delmas, M., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4791317 · Cited by 2
Evaluating Novel Unstructured Treatments with Generative AI: A Causal Prediction FrameworkPreprint
Ellickson, P. B., Kar, W., Reeder, J. C., & Zeng, G. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4845956 · Cited by 2
Chatbot or Humanaut? How the Source of Advice Impacts Behavior in One-shot Social DilemmasPreprint
Babin, J. J., & Chauhan, H. S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4853864 · Cited by 2
n, R. S. M. I., Ranger, N. A., Schimanski, T., & Leippold, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4878341 · Cited by 5
Dou, R. (2024) · Preprints.org · doi:10.20944/preprints202407.0120.v1 · Cited by 2
Future Approach Generative AI, Stylized Architecture, and its Potential in Finance
Bhatnagar, A. B., Nanad, A., Kumar, A., & Kumar, R. (2025) · Wiley eBooks · doi:10.1002/9781394271078.ch3 · Cited by 3
AI and Corporate Climate GovernancePreprint
Schirmer, J.-E. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5177547 · Cited by 2
A Survey on Hallucination in Large Language and Foundation ModelsPreprint
Ahadian, P., & Guan, Q. (2025) · Preprints.org · doi:10.20944/preprints202504.1236.v2 · Cited by 7
Can large language models reliably extract human disease genes from full-text scientific literature?Preprint
Yin, D.-Q., Leung, M., Pun, D. W. H., Chen, F. H., Kwon, J., Lin, X.-Y., & Ho, J. W. K. (2025) · bioRxiv · doi:10.1101/2025.07.27.667022
“…(e.g., "Heart and brain malformation syndrome(AR)" vs "SMG9-deficiency syndrome (Heart and brain malformation syndrome, OMIM #616920)"); and (3) Bias toward syndromic generalizations, likely rooted in pretraining corpora that over-represent high-level diagnostic labels (Ji et al., 2023).”
eidos: A modular approach to external function integration in LLMs
Aldana-Martín, J. F., Benítez‐Hidalgo, A., & Aldana-Montes, J. F. (2025) · SoftwareX · doi:10.1016/j.softx.2025.102290 · Cited by 3
LLM feedback for academic writing: Effects on students’ performance and engagement
Glüsing, R., Fleckenstein, J., Schmidt, F. T. C., & Möller, J. (2026) · Contemporary Educational Psychology · doi:10.1016/j.cedpsych.2026.102463 · Cited by 2
A Taxonomy of LLM-Supported Tasks for Critical AI Literacy in Journalism
Dierickx, L., Bjerknes, F., Opdahl, A. L., & Lindén, C.-G. (2026) · Postdigital Science and Education · doi:10.1007/s42438-026-00690-0 · Cited by 2
Feedback Loops With Language Models Drive In-Context Reward Hacking
Pan, A., Jones, E., Jagadeesan, M., & Steinhardt, J. (2024) · arXiv · doi:10.48550/arxiv.2402.06627 · Cited by 3
“…the pretraining data (Blodgett et al., 2020b;a; Rivera et al., 2024; Xu et al., 2024), output misinformation (Lin et al., 2021) and hallucinations (Ji et al., 2023), expose private training data (Carlini et al., 2020), and act deceptively (OpenAI, 2023a; Pan et al., 2023; Scheurer et al., 2023;…”
BackgroundHallE-Control: Controlling Object Hallucination in Large Multimodal Models
Zhai, B., Yang, S., Xu, C., Shen, S., Keutzer, K., Li, C., & Li, M. (2023) · arXiv · doi:10.48550/arxiv.2310.01779 · Cited by 2
“…al., 2022; Touvron et al., 2023b; Anil et al., 2023; Driess et al., 2023; Scao et al., 2022) Hallucination Before the emergence of LLMs, the NLP community characterized “hallucination” as the generation of content that either lacked coherence or deviated from its original source (Ji et al., 2023a).”
BackgroundQwen3-Coder-Next Technical Report
Cao, R., Chen, M., Chen, J., Cui, Z., Feng, Y., Hui, B., Jing, Y., Li, K., Li, M., Lin, J., et al. (2026) · arXiv · doi:10.48550/arxiv.2603.00729 · Cited by 2
“Though efficient due to zero padding, it inevitably incurs the notorious context hallucination problem (Ji et al., 2023).”
A State-Aware Dual-Tool Architecture for Improved Tool Use in Multi-Turn LLM Dialogue
Pałgan, B., Wawryszczuk, M., Chwał, J., Tkacz, E., & Dzik, R. (2026) · Applied Sciences · doi:10.3390/app16094329 · Cited by 1
Berges, V.-P., Oğuz, B., Haziza, D., Yih, W.-T., Zettlemoyer, L., & Ghosh, G. (2024) · arXiv · doi:10.48550/arxiv.2412.09764 · Cited by 46
“We refer to (Ji et al., 2023) section 5 for a comprehensive survey.”
The Bigger the Better? The Size of Language Models and the Dispute over Alternative Architectures
Förster, S. (2023) · A Peer-Reviewed Journal About · doi:10.7146/aprja.v12i1.140444 · Cited by 2
Zhang, Y., Zhou, D., Wang, Z., & Lai, Y. (2023) · Computer Speech & Language · doi:10.1016/j.csl.2023.101570 · Cited by 1
Generative AI: Citations for Trust and Consensus
Bax, E. T., Gerber, M., Giaffo, L., et al. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-47454-5_14 · Cited by 1
Evaluation Dimensions for Assessing Question Answer Systems for Lay Users: The Case of DiseaseGuru
Sukhwal, P. C., Kankanhalli, A., & Rajan, V. (2023) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v1i1.27484 · Cited by 1
Towards Self-Contained Answers: Entity-Based Answer Rewriting in Conversational Search
Sekulić, I., Balog, K., & Crestani, F. (2024) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3627508.3638300 · Cited by 8
Linden, K. C., Teakel, S. L., & Clatworthy, D. (2024) · Journal of Applied Learning & Teaching · doi:10.37074/jalt.2024.7.s1.4 · Cited by 5
Röser, A. M. (2024) · Soproni Egyetem Kiadó eBooks · doi:10.35511/978-963-334-499-6-roser-bartelt · Cited by 3
In-Context Learning for Scalable and Online Hallucination Detection in RAGS
Albanese, N. C. (2024) · doi:10.5121/csit.2024.140703 · Cited by 1
“…their training and retrieving rare or uncommon information [2, 3], as well as showing “hallucinations”, i.e., the creation of content that lacks either coherence or fidelity to the input source [4], hindering performances and posing obstacles for the adoption of LLMs in real-world applications.”
BackgroundBane and Boon of Hallucinations in the Context of Generative AI
Sakib, S. M. N. (2024) · Advances in business information systems and analytics book series · doi:10.4018/979-8-3693-2643-5.ch016 · Cited by 8
O futuro da pesquisa em inteligência artificial
Costa, A. H. R., & Cozman, F. G. (2024) · Revista USP · doi:10.11606/issn.2316-9036.i141p133-146 · Cited by 6
Generation of Market Comments and Outlooks in Mutual Fund Disclosure Documents Using LLM
Takano, K., Nakagawa, K., & Fujimoto, Y. (2024) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.39-4_fin23-b · Cited by 1
Lessons Learned on Summarizing Legal Documents Combining Reinforcement Learning and ChatGPT
Silva, E. H. M. D., & Ladeira, M. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-64779-6_40 · Cited by 1
Variable Assignment Invariant Neural Networks for Learning Logic Programs
Phua, Y. J., & Inoue, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71167-1_3 · Cited by 4
“With the advent of large language models (LLM), there have been renewed interests [13] in combining symbolic reasoning with LLMs [17].”
BackgroundRocha, C. T., Hankala, I., Mekuria, L., et al. (2024) · Journal of the Society for Clinical Data Management · doi:10.47912/jscdm.363 · Cited by 1
A framework for integrating GPT into geoscience research
Sufi, F. K. (2024) · Journal of Economy and Technology · doi:10.1016/j.ject.2024.10.003 · Cited by 1
Towards Building a Robust Knowledge Intensive Question Answering Model with Large Language Models
Hong, X., Shao, Y., Wang, Z., Duan, M., & Jin, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9431-7_18 · Cited by 1
Towards Enhancing Linked Data Retrieval in Conversational UIs Using Large Language Models
Mussa, O., RANA, O. F., Goossens, B., Orozco‐terWengel, P., & Perera, C. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0573-6_18 · Cited by 5
A Survey of Recent Advances in Commonsense Knowledge Acquisition: Methods and Resources
Wang, C., Li, J., Chen, Y., Liu, K., & Zhao, J. (2025) · Machine Intelligence Research · doi:10.1007/s11633-023-1471-3 · Cited by 12
Gleßmer, M. S., & Forsyth, R. (2025) · Teaching & Learning Inquiry The ISSOTL Journal · doi:10.20343/teachlearninqu.13.4 · Cited by 5
“This is despite the issue of “hallucinations,” described as “text that is nonsensical, or unfaithful to the provided source input” (Ji et al. 2023, 248).”
Development of the Automated Question-Answering System Specialised in the Tourism Field
Smirnov, N. V., & Георгиевич, М. А. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-3-031-82494-4_26 · Cited by 1
CyGPT: Knowledge Graph-Based Enhancement Techniques for Large Language Models in Cybersecurity
Ou, L., Ni, X., Wu, W., & Tian, Z. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00036 · Cited by 4
“They may inadvertently apply learned knowledge incorrectly, resulting in plausible yet erroneous outputs [13], [14].”
Ambiguity Resolution in Vision-and-Language Navigation with Large Language Models
Wei, S., Wang, C., & Qi, J. (2024) · IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · doi:10.1109/iciba62489.2024.10868019 · Cited by 2
“Nevertheless, there are also some limitations associated with VLN methods based on LLMs [16], [17].”
An Efficient Approach for Enhancing GenAI Trustworthiness
Yehezkel, A. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00292 · Cited by 2
“…two major issues of LLMs’ truthfulness are hallucination and misinformation generation, both of which can be addressed by the new approach: • Hallucination: One of the significant challenges associated with LLMs is their tendency to generate information not based on their training data [3]–[5].”
A dual adversarial structure of generative adversarial network for nature language generation
Sue, K.-L., & Chen, Y.-C. (2025) · Industrial Management & Data Systems · doi:10.1108/imds-05-2024-0435 · Cited by 2
Bona, J. P. (2024) · Yearbook of Medical Informatics · doi:10.1055/s-0044-1800747 · Cited by 2
“However, their limited ability to understand [22], propensity to “hallucinate” (make things up) [23], and limited ability to reason [24] pose challenges that may best be addressed by solutions that combine LLMs with other AI techniques best-suited for such tasks.”
Zhang, J., Li, X., Fang, J., Wei, W., & Cui, M. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4298-4_3 · Cited by 1
EmotioNotes Dataset: Decoding Emotions in Classical Music Through Concert Program Notes
Khanal, P., & Donnelly, P. J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-90167-6_23 · Cited by 1
Double-Feedback: Enhancing Large Language Models Reasoning in Robotic Tasks by Knowledge Graphs
Wang, H., Zhang, S., Wang, S., Jiang, T., & Ge, Y. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3562776 · Cited by 4
Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model Supervision
Pan, Y., Hong, J., Zhao, T., Song, L., Liu, J., & Shang, X. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714685 · Cited by 1
Improving Next Tokens via Second-to-Last Predictions with Generate and Refine
Schneider, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91398-3_17 · Cited by 2
“Our method falls into the generation-time category [15] or post-processing category [8,24], as we first generate a token before potentially altering it.”
Knowledge-guided large language models are trustworthy API recommenders
Wei, H., Su, X., Zheng, W., Tao, W., Yu, H., & Kuang, Y. (2025) · Automated Software Engineering · doi:10.1007/s10515-025-00518-4 · Cited by 2
ELWARD : Empowering Language Model With World Insights and Human‐Aligned Reward Design
Yong-ping, D., Li, S., Yan, R., Hou, Y., & Han, H. (2025) · Expert Systems · doi:10.1111/exsy.70055 · Cited by 1
“It leads to model outputs de-viating from social norms or user expectations, a phenomenon referred to as ‘Hallucinations’ (Ji et al. 2023).”
Mohamed, S., Ismail, N., Amaya, K., Parvin, A., Oliver, M. D., & Parra, E. (2025) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3715669.3725868 · Cited by 3
“A recurring issue is hallucination, where the model generates inaccurate or misleading descriptions that misrepresent the actual code behavior, making detection in code summarization challenging due to the need for both syntactic and semantic accuracy [Ji et al. 2023].”
Nicholas, D., Abrizah, A., Clark, D., Bravo, B. R., Revez, J. M. R., Herman, E., Świgoń, M., Xu, J., & Watkinson, A. (2025) · Learned Publishing · doi:10.1002/leap.2015 · Cited by 2
“On the other hand, AI is notorious for its tendency to ‘hallucinate’—that is, to produce texts that give the impression of being fluent and natural, despite being unfaith-ful and nonsensical, and to invent non-existent citations (Ji et al. 2023; Ngwenyama and Rowe 2024).”
ChatMolData: A Multimodal Agent for Automatic Molecular Data Processing
Yu, Y., Wang, H., Zong, L., Chen, B., Li, Y., & Yu, X. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202401089 · Cited by 2
Degen, H., Min, Z., & Nagaraja, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93412-4_3 · Cited by 1
Do Large Language Models Require Prior Knowledge for Learning? A Preliminary Study
Soll, M., & Kobras, L. (2025) · IEEE Global Engineering Education Conference (EDUCON) · doi:10.1109/educon62633.2025.11016655 · Cited by 1
“While the concept of hallucinations / confabulation as made-up outputs for AI tools is not new [19], it was nonetheless interesting to see that Copilot vehemently tried to teach a student about book vending machines after the student accidentally asked for information regarding “B¨uchli automata” 1…”
Radah, T. (2025) · Journal of Information Systems Engineering & Management · doi:10.52783/jisem.v10i53s.10967 · Cited by 3
MedConMA: A Confidence-Driven Multi-agent Framework for Medical Q&A
Wang, R., Chen, Y., Zhang, W., Si, J., Guan, H., Peng, X., & Lü, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8180-8_33 · Cited by 7
Towards Retrieval-Augmented Large Language Model-Based Conversational Recommender System
Yang, D., & Wang, F. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8180-8_25 · Cited by 6
Hallucination Detection in Large Language Models Using Diversion Decoding
Abdeen, B., Siddiqui, S. M. T., Ahmed, M. T., Singhal, A., Khan, L. R., Modi, P. P., & Al-Shaer, E. S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-96590-6_7 · Cited by 1
“Although LLMs have demonstrated high performance in various tasks, their reliability as a source of information is limited due to their tendency to hallucinate [12,14].”
SecRAG: A Graph-Enhanced RAG Framework with Dynamic Prompt for Cybersecurity Applications
Qiao, Y., Li, L., Cheng, F., Zhang, J., Gao, J., & Zhu, H. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033478 · Cited by 2
“Yet, conventional LLMs lack sufficient domain-specific knowledge, leading to imprecise responses [7] and the generation of hallucinations—plausible but incorrect information—which is particularly risky in cybersecurity [8].”
Evaluating the Effects of Prompt Perturbation on Bias and Hallucination in Large Language Models
Yousefi, M., Shahi, A., Sharifi, M., Romera, A. J. J., Hoermann, S., & Piumsomboon, T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6588-4_25 · Cited by 1
“LLMs can generate hallucinations [26], produce adversarial responses, and exhibit biases [6, 33].”
Lahrsow, M. (2025) · BIBLIOTHEK Forschung und Praxis · doi:10.1515/bfp-2025-0002 · Cited by 1
Walking Backward to Ensure Risk Management of Large Language Models in Medicine
Onitiu, D., Wachter, S., & Mittelstadt, B. (2025) · The Journal of Law Medicine & Ethics · doi:10.1017/jme.2025.10132 · Cited by 7
“98 Therefore, the provider needs to examine how different intended uses produce trade-offs for risk estimation and control.”
Guo, T., Wang, C., Liu, Y., Tang, J., Li, P., Sai, X., Yang, Q., Gao, X., Li, Z., & Wen, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130931 · Cited by 7
Wang, B., Bai, Z., Wang, Q., Lin, J., Yang, M., Zeng, X., & Xu, R. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730232 · Cited by 9
Exploring the integration of large language models in industrial test maintenance processes
Liu, J., Lemner, L., Wahlgren, L., Gay, G., Mohammadiha, N., & Wennerberg, J. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.113049 · Cited by 10
EduRAG:A RAG Framework for Academic Expert Recommendation
Li, Y., & Zheng, L. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9815-8_15 · Cited by 2
Qin, H., Yang, Z., Tong, C., & Jiang, L. (2024) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc64274.2024.00148 · Cited by 1
“To avoid the hallucination problem [28] often associated with multimodal large language models, we design prompts incorporating labels from the training data.”
Making Generative AI Hallucinations Useful by Reassessing the Troublemaker Agent Strategy
Blanchard, E. G., Callahan, J.-C., Akretche, I., Asswiel, N., Schmitt, L., Kessemtini, A., & Afizullah-Khan, I. S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-99264-3_36 · Cited by 1
Comparison of Generative Artificial Intelligence and Student-Generated Veterinary Handouts
Gibson, R., Tomberlin, S. S., Mackay, L., & Foradori, C. D. (2025) · Journal of Veterinary Medical Education · doi:10.3138/jvme-2025-0003 · Cited by 2
Performance of Large Language Models in the Cognitive Analysis of Misinformation: Evaluation Study
Wojtczak, D. N., McQuire, C., Zuccolo, L., Peersman, C., & McConville, R. (2025) · JMIR Infodemiology · doi:10.2196/72524 · Cited by 1
“However, LLMs can generate hallucinations, which can be defined as possible but incorrect or misleading information [42].”
Li, C., & Zhang, M. (2025) · Annals of the New York Academy of Sciences · doi:10.1111/nyas.15388 · Cited by 3
Trapped in the Prompt Loop: Reprompt Behavior in Writing with ChatGPT
Jung, H., Jeong, Y., & Lee, J. (2025) · International journal of human computer interactions · doi:10.1080/10447318.2025.2530100 · Cited by 4
“LLMs can also generate responses that appear plausible but are inaccurate or inconsistent with facts, leading to issues known as hallucinations (Ji et al., 2023; Naveed et al., 2023; Yoo et al., 2025; Zhang et al., 2023).”
The Evolution of Chatbots: From Rule-Based to GPT Models
Aishwarya, S., Selvamurugan, C., G, P. K., Prabhakar, J. M., Raja, J. T., & Amrutha, V. J. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9841-8.ch008 · Cited by 1
Architecting Scalable ChatGPT Solutions for Enterprise
Banerjee, M. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9841-8.ch007 · Cited by 1
Adaptive-TOD: An LLM-driven and adaptive agent for diverse interaction modes
Li, P., Yang, Q., Xu, S., Li, X., Li, Z., Chen, W., Liu, Y., Guo, T., Tang, J., & Wen, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130991 · Cited by 4
VeriRAG: Design AI-Specific CPU Co-processor with RAG-Enhanced LLMs
Bai, K., Yan, P., Liu, L., & Jia, T. (2025) · International Symposium of Electronics Design Automation (ISEDA) · doi:10.1109/iseda65950.2025.11100783 · Cited by 2
“These design-specific details can prevent hallucinations [26] in subsequent code generation. summarized code is split by Verilog-adapted Recursive-Text-Splitter, to generate summary set and corresponding code set.”
Paseri, L., & Durante, M. (2025) · Cambridge University Press eBooks · doi:10.1017/9781009492553.006 · Cited by 2
MCTA4R: Enhancing User Preference Alignment with Meta-CoT and Search Algorithms
Huang, R., Li, B., Zhao, X., Xu, M., Wu, W., & Zhu, Q. (2025) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai65741.2025.11108609 · Cited by 1
“A notable concern involves the potential for hallucination [5], [11] or the generation of inaccurate information, thereby compromising the reliability of agent outputs.”
Peignier, S., Van, A. L., Meunier, Y., Pauliat, E., Zouari, M., & Calevro, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-01436-8_14 · Cited by 2
Designing Trustworthy AI Systems for PTSD Follow-Up
Cazares, M. F., Miño, J., Ortiz, I., & Andrade, R. (2025) · Technologies · doi:10.3390/technologies13080361 · Cited by 1
Yu, M., Wang, J., Chen, Y., Lepech, M. D., Liu, Y., & Law, K. H. (2025) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac65507.2025.00081 · Cited by 1
“, [1, 0, 1], [2]) Make sure the answer is complete in no more than 150 words.”
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.




