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 3,901–4,000 of 4,844
Wen, C.-M., & Ierapetritou, M. (2026) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2026.109792 · Cited by 1
ADVENT: LLM-Driven Automatic Predicate Invention for ILP
Yu, T., Huang, P.-C., Hsu, C., Ku, C.-T., & Kang, Y. (2026) · 2026 IEEE International Conference on Information Reuse and Integration for Data Science (IRI) · doi:10.1109/iri69576.2026.00025
“However, relying solely on LLM reasoning introduces reliability concerns [9].”
Self-citationEvaluating LLM-Generated Wikipedia Content: Political Topics in a French Setting
Vermeirsche, J., SanJuan, É., & Jiménez, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29532-3_18
Vora, A., Parpia, S., & Gada, T. N. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-30836-8_22
Using Generative AI to Discover Ancient Civilizations
Zhang, C., Saad, S., Palazzolo, T., Reynolds, R. G., O’Shea, J. M., Lemke, A., & O'Shea, C. M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-30836-8_34
Jafaraghaeian, D., & Butvilas, T. (2026) · Applied Business Issues & Solutions · doi:10.57005/ab.2026.2.9
The 1% problem: LLM orchestration for rare event detection in manufacturing supply chains
Dang, J., Vedova, J. D., & Yang, Y. (2026) · International Journal of Production Economics · doi:10.1016/j.ijpe.2026.110119 · Cited by 1
Persona Diversity: Comparing Usability-Testing Outcomes Across Heterogeneous Personas
Baek, Y., Tozer, C., Ghimire, A., & Nizamani, S. B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30846-7_16
Potential and limitations of LLMs for augmenting lexical knowledge bases
Torrielli, F., Siragusa, G., Rulfi, V. L., Rapp, A., & Di, L. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133545
Gupta, R., Knight, T., & Nagakura, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30846-7_7
Postmodern epistemik galat paradoksu: Üretken yapay zekâ kullanımı için bir etiketleme çerçevesi
Öncü, S. E., Bozkurt, A., Elibol, H., & Özer, F. (2026) · Açıköğretim Uygulamaları ve Araştırmaları Dergisi · doi:10.51948/auad.1922925
Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
Xie, Z., & Sun, Z. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582530 · Cited by 4
“However, their reliance on parametric knowledge introduces a critical challenge: hallucination, where the generated content deviates from factual correctness [3], [4].”
Jang, S., Myoungrak, L. E. E., & Shon, T. (2026) · Electronics · doi:10.3390/electronics15132949
“Furthermore, owing to the high reliability demanded by security analysis tasks, controlling the inherent hallucinations in generative models is essential [13].”
Exploring OpenClaw’s potential for adaptive, self-hosted educational AI
Baradziej, S., & Pal, R. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1859178
Akyol, H. M. (2026) · AI and Ethics · doi:10.1007/s43681-026-01231-y
“The term builds on epistemic hallucination—confident generation of factually false content [17]—while extending it to the nor - mative domain.”
LLM-Enhanced Rapid Review (LLMEn-RR): a methodology proposal
Irace, M. B., Simões, J. L., Argôlo, M., Barbosa, C. E., Nóbrega, L., Martinez, L. F., & de Souza, J. M. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582469
“Moreover, LLMs remain prone to hallucinations and factual inconsistencies, as discussed by Ji et al. [12], making human oversight indispensable.”
Leveraging Artificial Intelligence in legal research: Editor’s insights
Stepanova, V. V. (2026) · Вестник Российского университета дружбы народов. Серия: Юридические науки · doi:10.22363/2313-2337-2026-30-2-250-273
MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive Abstraction
Li, Y., Chen, X., Jiang, M., Tang, W., & Wang, G. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582204
“One major limitation is the lack of factual grounding, where models frequently fail to track specific character identities, resulting in hallucinated descriptions [9].”
MSKGCF: A Framework for Multimodal Scientific Knowledge Graph Construction and Fusion
Maoliniyazi, A., Ma, C., & Meng, X. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581529
“…potential in information extraction [6], directly applying them creates a dilemma: General LLMs are prone to hallucinations and high inference costs in zero-shot settings [7], whereas smaller domain-specific models often lack the comprehensive reasoning capabilities to handle complex layouts.”
Controllable Narrative Rendering for Enhanced Assisted Writing
Lü, M., Liu, Y., Wu, J., Zhang, J., Wang, Q., Hu, Y., Li, Y., & Xu, Y. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582135
“General-purpose models tasked with enhancement either default to safe, surface-level editing [5], which amounts to remedial polishing, or generate uncontrolled plot expansions when prompted for expressivity, often effectively hallucinating new events [6].”
Self-citationDuah, P., & Awuah-Offei, K. (2026) · SoftwareX · doi:10.1016/j.softx.2026.102819
Huang, Y., Tao, J., Luo, J., He, Y., & Shen, W. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582444
“…reasoning and generation capabilities in general tasks, but they still exhibit obvious instability in dealing with domain-specific and precise industrial knowledge tasks—their probability of generating hallucinatory information in technical Q&A and structured retrieval tasks can reach 15%-30% [4].”
Radar Algorithm Generation System Based on Domain-Adaptive Retrieval-Augmented Generation
Hu, L., Jia, Y., Zhao, B., Xie, M., Li, Y., & Dong, K. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582809
Beyond Correctness: Measuring Hallucination Impact in AI-Assisted Development Workflows
Gupta, S., Vanteru, K., Reddy, P. K., & Sunkireddy, S. (2026) · International Conference on Innovations in Emerging Technologies for Sustainable Development (ICIETSD) · doi:10.1109/icietsd68684.2026.11584879
Shin, C., Park, J. H., Kim, S. J., Lee, Y. H., & Lee, H. S. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02109-5
Furtado, N. G., & Furtado, J. V. (2026) · Research Square · doi:10.21203/rs.3.rs-10255415/v1
Rosa, M. B. S., França, J., Siqueira, M. T. S., & Raineri, C. (2026) · Veterinary and Animal Science · doi:10.1016/j.vas.2026.100761
“:P imbalance, the AI models statistically learn that diets with inadequate ratios are the dominant pattern in their training data, not the exception (Ji et al., 2023).”
A Hybrid Multi-level Retrieval Architecture for an AI Assistant in University Admissions Support
Radaeva, A., Stepanov, N., Suleykin, A., Panfilov, P., Pyatetsky, V., & Egorova, K. A. (2026) · International Conference on Technology Enhanced Learning in Higher Education (TELE) · doi:10.1109/tele71748.2026.11591353
“The use of large language models without external grounding may lead to unreliable responses due to hallucination effects [1].”
Evidence-Grounded Interactive AI for Adaptive Medical Education
Zhuang, Y., Guo, Y., Ju, L., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29178-3_16
Tarek, S., Saied, Y., Emad, Y., Mohamed, M., Mohamed, I., Wageh, A., Tawfik, M., & Badawy, W. (2026) · International Conference on Machine Intelligence and Smart Innovation (ICMISI) · doi:10.1109/icmisi69868.2026.11584039
“This phenomenon has been widely documented in the literature and represents a structural limitation of parametric language models rather than a mere implementation flaw [10], [22].”
Artificial Intellegence in Studentsʼ Academic and Vocational Activities
Булан, И. Г., Александровна, П. М., Nesyna, S. V., & Ponikarovskaia, V. V. (2026) · International Conference on Technology Enhanced Learning in Higher Education (TELE) · doi:10.1109/tele71748.2026.11591340
ElSamman, I., & Safy, M. (2026) · International Conference on Machine Intelligence and Smart Innovation (ICMISI) · doi:10.1109/icmisi69868.2026.11584228
Banaybanay, R. J., & Ricafort, R. B. (2026) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2026.150600080
Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation
Aktaş, Y., Yi̇ği̇t, T., Ersoy, M., & Üncü, İ. S. (2026) · Advances in Artificial Intelligence Research · doi:10.54569/aair.1894025
Liu, C.-W., Qu, R., Yu, J., Jin, F., He, J.-L., Wang, J.-T., & Pan, J.-W. (2026) · Journal of engineering design · doi:10.1080/09544828.2026.2698388
Velentza, A.-M., Guyader, J., Billardon, C., Andries, M., Bosser, A.-G., & Lohr, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29586-6_15
VulLens: Enhancing Software Vulnerability Detection against Evasion Attacks
Sun, S., Sharma, P., Maitra, S., Stavrou, A., & Wang, H. (2026) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn69566.2026.00025
Exploring motivations, response quality, and fit in ChatGPT-assisted information tasks
Li, Y., & Marcum, J. H. (2026) · Journal of Librarianship and Information Science · doi:10.1177/09610006261461308
Bounia, L., & Ndour, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30849-8_2
Efficient Bug Detection by Inferring Implicit API Contract of Pointer State Transition
Deng, X., Ma, Y., Gao, X., & Sun, H. (2026) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn69566.2026.00035
“Second, we engineer our prompts to require Chain-of-Thought (CoT) [30] reasoning to help us keep the reliability of LLM [31].”
Chhabra, P., Negi, M., Goje, O., Singh, D. P., & Khan, F. (2026) · International Conference on AI, Data Science, Cyber Security and Smart Manufacturing for Sustainable Development (ICADCS) · doi:10.1109/icadcs70036.2026.11583318
“However, hallucinations remain a key barrier to deployment [11], [15].”
InfluentialLang, S., Motov, S., Krueckel, J., Scherer, J. N., Staartjes, V. E., & Wuertz‐Kozak, K. (2026) · JOR Spine · doi:10.1002/jsp2.70203
“Given the documented tendency of LLMs to generate plausible but non-verifiable statements in unconstrained settings [59, 60], their role in omics analysis should be limited to structured, evidence-bound interpretation layers that operate down-stream of validated statistical pipelines rather than…”
KAPT: Knowledge-Augmented Prompt-Tuning Framework for Aspect-Based Sentiment Analysis
Zhang, Z., Wang, Y., Li, B., Song, H., Wu, H., & Wang, J. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3708933
“Such hallucination issues [53] lead to high overall accuracy scores, primarily due to strong performance on explicitly positive and negative samples, while yielding suboptimal Macro-F1 results.”
Generative Language Models-Based System for Automatic Short Answer Scoring with Feedback
Sayeed, M. A., Gupta, D., & Kanjirangat, V. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.123
Lightweight Adapted Retrieval-Augmented Inference Network for Legal Issues
钱泓廷, Lin, J., Tang, J., Zhou, H., Peng, Y., Liu, L., & Liu, X. (2026) · Electronics · doi:10.3390/electronics15142996 · Cited by 1
“This inherent limitation renders them prone to “hallucination”—the generation of plausible yet factually incorrect content—when confronted with complex legal reasoning tasks that require up-to-date, authoritative external knowledge support [1,2].”
Uncovering Reasoning Failures: Hallucination Detection via Semantic Probing and Attention Tracking
Dong, F., Yue, X., Chen, Y., & Shi, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2480-7_23
Generative-AI Powered InferencePreprint
Duan, J., & Pelger, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7053778
Li, J., Huang, S., Qiu, Y., Chen, W., Zhang, Y., Zhao, X., Qu, G., Bu, Y., Feng, X., Xu, J., et al. (2026) · JMIR Metascience and Research Integrity · doi:10.2196/preprints.105947
Re-KGR: Mitigating Factual Hallucinations via Hybrid Graph Reasoning and Semantic Refinement
Li, Y. Z., Wang, X., Liu, R., Wang, M. Y., & Luo, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2494-4_16
Kandasamy, S., Arumugam, S., & Jayapal, C. (2026) · Research Square · doi:10.21203/rs.3.rs-9834249/v1
Shantanu, S. K., Pial, S. M. R., & Sharmin, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30784-2_19
A Virtual Agent for Talent-Job Alignment Using Generative AI and Hybrid Retrieval Mechanisms
Jain, S., Prasad, P., Azeem, M., Kaul, P., & Kumar, M. (2026) · IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT) · doi:10.1109/ic2pct68894.2026.11584272
“The system instructions explicitly constrain the model to only use information present in the resume, reducing hallucination risk [10].”
Retrieval-Augmented Generation System for Academic Knowledge Access
Flego, A., & Mekterović, I. (2026) · MIPRO ICT and Electronics Convention (MIPRO) · doi:10.1109/mipro70003.2026.11591646
“However, when used independently, LLMs may generate responses that are not grounded in verified sources and can exhibit hallucinations, producing factually incorrect or unsupported statements, which limits their reliability in academic settings [2], [3].”
Paoli, D., Lanza, M., Banchelli, F., Boarini, M., Borghi, S., Sangiorgi, L., & Mordenti, M. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1807607
“This is due to the partial absence of structured semantic relationships in ICD-9-CM above mentioned, coupled with the relative lack of terms compared to more up-to-date coding systems, aspect which limits the model’s ability to anchor itself to a solid ontological “ground truth” (44).”
PharmaSage: Knowledge Graph-Driven RAG for Reliable Drug Discovery with LLMs
Reddy, J. S., Chowdary, A., Reddy, G., & Surendran, S. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.125
PromptED: An Interactive Tool for Generative AI Literacy for Media Professionals
Novak, J., Tang, A., & Sowder, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30784-2_15
Telfah, S. M., Ahmed, S. A., & Elsori, D. H. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1797327
Yanes, N., Jitkajornwanich, K., Kee, K. F., & Perlmutter, D. D. (2026) · Journal of Broadcasting & Electronic Media · doi:10.1080/08838151.2026.2691175 · Cited by 3
“LLMs generate unsupported statements with particular frequency when retrieved contexts are low quality or poorly matched to claims (Ji et al., 2023; Kalai et al., 2026; Shin et al., 2022; Zhang et al., 2026).”
Wang, C., Li, C., Wang, P., Zhang, L., Liu, S., 祁吉, Hu, J., Cai, Y., Zhao, H., & Pu, R. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104997 · Cited by 2
RED: Retrieval-enhanced knowledge distillation for smaller language models
Li, X., Peng, S., Wakamiya, S., & Aramaki, E. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133599
Towards trustworthy LLM-assisted EPD comparability assessment for circular construction materials
Chen, Y., Sun, N., & Xue, J. (2026) · Environmental Impact Assessment Review · doi:10.1016/j.eiar.2026.108606 · Cited by 1
Poudel, A., Barrios, C., Torre, P. D. L., Mehta, V., & Silwal, S. (2026) · Discover Cities · doi:10.1007/s44327-026-00323-y · Cited by 1
“Traditional governance mechanisms, designed for deterministic systems, do not accommodate the opaque and probabilistic nature of modern AI [26, 27].”
Towards Trustworthy AI: A Comprehensive Framework for Evaluating Model Safety Across Dimensions
Hasan, M. M., Logofătu, D., & Ray, J. K. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-31141-2_25
HIVE: Understanding Post-hallucination Reasoning in Vision Language Models
He, F., Wang, Z., Wang, Q., Guan, Q., Liu, D., Tang, R., & Li, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_34 · Cited by 2
Abesadze, N., Fernandes, A., & Rubin, E. (2026) · Cureus · doi:10.7759/cureus.112306
Chen, Y., Zeng, Z., & Hassan, M. S. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1784200
“Such issues are particularly prominent in legal text analysis tasks, as models often produce seemingly plausible yet unfounded interpretations of clauses, case matches, or legal conclusions (Ji et al., 2023).”
Zhang, Y. J., Zhang, Y., Zheng, K., Chen, T., & Yin, H. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809600 · Cited by 3
Beyond Fluency: Toward Reliable Trajectories in Agentic IR
Sinha, A., Ranganathan, S., Das, D., & Dharmaratnakar, A. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808511 · Cited by 3
Pan, J., Pan, X., & Pan, H. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1818923
Reconstruction of Translator Co-Subjectivity and Translation Teaching Innovation in the GenAI Era
郎, 柯. (2026) · Modern Linguistics · doi:10.12677/ml.2026.147635
BOLE: A script-knowledge driven multi-agent framework for reproducible llm-assisted genomic breeding
Wang, Z., Liang, C., Zhang, Y., Zhou, R., Zhang, X., Wei, W., & Li, K. (2026) · Journal of Integrative Agriculture · doi:10.1016/j.jia.2026.07.011 · Cited by 3
Uncertainty-Aware Context Compression for Retrieval-Augmented Generation: A Training-Free Framework
Li, Z., Zhao, S., Wang, M., & Zhao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2862-1_8
Possible Distillation for Abstractive Summarization: Reducing Hallucination in Compact LLMs
Abishethvarman, V., Balasubramaniam, G., Prasanth, S., Kumara, B. T. G. S., & Kuhaneswaran, B. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0137-2_15
Yuan, N., & Zhao, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2859-1_5
RAG-Based Enterprise Knowledge Platform: Design and Evaluation
Zhang, Z., Zhang, Y., & Zhou, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2852-2_5
Cognitive Mycelium: A Federated Knowledge Management Architecture with Graph-Enhanced Retrieval
Ye, Z., & Liu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2856-0_31
Yüksel, A. S. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108251
MedConf-RAG: Reliable Medical LLMs with Gated Graph Integration and Conformal Factuality Guarantees
Huang, X., Bu, Y., Zhang, N., Zhang, Y., Sheng, H., & Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2856-0_39 · Cited by 1
Pecher, P., Kegel, F., & Kolbe, L. M. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10790-8 · Cited by 1
Neuro-Symbolic RAG for ISO 21001-Compliant Educational Document Generation
Zouari, A., Ketata, M., & Loukil, Z. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-30809-2_23
Farhan, K. A., Li, Y., & Xue, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2859-1_1
Maghsoudlou, A. (2026) · Springer eBooks · doi:10.1007/978-3-032-21685-4_15
Dou, L., Gong, S., Qiujie, S., & Varlamov, O. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3447-9_38
Harsha, M., Buduru, A. B., & Biswas, S. K. (2026) · Acta Astronautica · doi:10.1016/j.actaastro.2026.07.003
Maheshwari, P., Chand, K., Rama, P., et al. (2026) · International Conference on Next Generation Electronics (NELEX) · doi:10.1109/nelex69209.2026.11590397
“Large language models have been shown to be very powerful at capturing relevant clinical knowledge [6] and at synthesizing documents from documentation [7] but they are susceptible to hallucination when the source of the information has not been verified.”
Li, H., Uygun, Ö., Yu, X., Zhou, Y., Yang, Z., & Chen, C. (2026) · Computers & Industrial Engineering · doi:10.1016/j.cie.2026.112240 · Cited by 1
Retrieval-Conditioned EEG Report Generation for Interictal Epileptiform Discharge Detection
Zhu, Y., Jiang, J., Shu, X., & Chen, D. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3498-1_28
Surfacing the Invisible: AI and the IS Discipline
Agarwal, R., Padmanabhan, B., & Liu, Y. (2026) · ACM Transactions on Management Information Systems · doi:10.1145/3828556
“The methodological literature has begun to characterize the visible failure modes, including hallucination [Ji et al. 2023] and the components of variance that separate reliable from unreliable LLM-based measurement [Camuffo et al. 2025].”
Thode, M., & Paliokas, I. (2026) · Computers · doi:10.3390/computers15070443
Adiniaev, Y., Omar, M., Daniel, O., Timor, T. M., Barash, Y., Brook, O. R., Klang, E., & Gorenshtein, A. (2026) · Neurological Sciences · doi:10.1007/s10072-026-09239-2
“However, LLMs may produce fluent but factually incorrect outputs (hallucinations), and this failure mode is most con - sequential when the clinical task requires a single correct answer [ 11, 12].”
The Flaw of Perfection: How University Professors Identify the Inauthentic Voice of AI
Shehab, E., & Alkhateeb, M. (2026) · Journal of Academic Ethics · doi:10.1007/s10805-026-09755-y
“They also attend to fac - tual inconsistencies where fabricated citations or non-existent data sources are confidently presented (Ji et al., 2023; Latif, 2025; Maleki et al., 2024; Watson, 2024).”
Ayalew, A. M., Seppänen, T., & Oussalah, M. (2026) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3805713.3820416
Sui, C.-J., Huang, Y.-N. K., Sreedevi, P. S., Liu, S.-Y., & Chang, C.-Y. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2026.2691906
DECODE: DEcoupled Evidence COnstrained Dynamic Exploration for Multi-hop Knowledge Graph Retrieval
Lu, Y., Zou, L., & Jiang, M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3444-8_18
Zhao, J., Yu, T., Yuan, F., Zhou, Y., Wang, Y., Cao, C., & Liu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3444-8_21
Self-citationDesigning a Local RAG-Based Intelligent Tutoring System for Domain-Specific Education
Gala, A. D. C. O. S., Marcondes, F. S., Machado, J. M., & Nováis, P. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2891-1_13 · Cited by 2
SRAG: A Lightweight and Specialized Retrieval-augmented Generation System at the Edge
Luo, R., Xing, Z., Gu, L., Wu, S., Jin, H., & Xia, X. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809702
Hallucination Detection and Reduction in Large Language Models: A Practical Study
Rajput, K., H, A. B., Smitha, G., V, M, H. K., M, M. K. Y., & Kanbargi, M. (2026) · International Conference on Emerging Trends in Mobile Computing and Sustainable Informatics (ICEMCSI) · doi:10.1109/icemcsi67638.2026.11603013
“Ji et al. [6] identified key contributing factors such as noisy training data, probabilistic text generation, and limited access to real-world knowledge.”
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.




