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 4,701–4,800 of 4,840
Mohammed, M. B. R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-39783-6_9
From Cloud to Pocket: Frontier Edge Foundation Models and the Future of Clinical Informatics
Shankar, R. (2026) · Applied Clinical Informatics · doi:10.1055/a-2969-1166
Shinoz, T., & Niranjana, G. (2026) · Technology and Innovation Conference (TIC) · doi:10.1109/tic68483.2026.11703004
Localizing Hallucinations in LLM-Based Robot Action Traces
Geliev, A., Rieder, J. S. I., Aschenbrenner, D., & Gries, T. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-38610-6_37
Colson, H., & Ballard, H. O. (2026) · Medical Science Educator · doi:10.1007/s40670-026-02907-0
Can, B., Agar, A., & Arslan, İ. (2026) · Digital Health · doi:10.1177/20552076261486992
Evaluating the Effectiveness of LLMs Against Manual Searches for Scientific Literature Retrieval
Acosta-Madrigal, C., Mena-Rodríguez, F., Pereira-Cerdas, L., Gonzalez-Villanueva, R., & Hidalgo‐Céspedes, J. (2026) · IEEE Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI) · doi:10.1109/jocici69279.2026.11701711
“In the context of scientific search, hallucinations correspond to non-existent references generated by LLMs. Hallucination constitutes a widely documented critical limitation [9], [12], [13].”
Abouzeid, E., & Sallam, M. A. (2026) · Medical Science Educator · doi:10.1007/s40670-026-02909-y
Kumar, J. D. S., Shashidhar, M., Reddy, A. U. M., Ali, M. S., B.Mounika, & K.Sreenivasulu (2026) · International Conference on Secure Information Systems and Technologies (ICSIST) · doi:10.1109/icsist70215.2026.11706042
“Hallucination [4] is still a big problem in RAG systems as well: even though external knowledge has been used, hallucination.”
Artificial Intelligence Driven Smart Smile Mentor Chatbot to Transform Oral Care
Sharma, S., & Agarwal, P. K. (2026) · doi:10.1109/icsist70215.2026.11705802
“Significant drawbacks relate to the risks of generating responses based on hallucinations – clinical data that does not have anything to do with reality and requires implementing systems of human supervision and additional data retrieval [13].”
Marimuthu, G. (2026) · Technology and Innovation Conference (TIC) · doi:10.1109/tic68483.2026.11702955
“Generative models brought about agents that could deal with natural language input and unstructured data, but at the same time, they provided new vectors for attacks [11].”
Evaluating Retrieval-Augmented Generation Systems: A System-Level Perspective
Joshi, P., & Sawant, N. (2026) · Technology and Innovation Conference (TIC) · doi:10.1109/tic68483.2026.11702925
“Despite all this progress, LLMs still rely heavily on parametric knowledge encoded in their weights, which can result in hallucinations, stale information, and factual errors in knowledge-intensive settings [2].”
Kang, J.-H., Lee, S.-H., & Bae, Y.-S. (2026) · World Electric Vehicle Journal · doi:10.3390/wevj17100507
Daniele, F., Montini, E., Conti, L., Gambardella, L. M., & Pedrazzoli, P. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-38610-6_3
Large Language Models and Agentic AI for Vulnerability Management: A Systematic Review
Akrami, Y., Malkawi, M., & Alhajj, R. (2026) · Expert Systems · doi:10.1111/exsy.70437 · Cited by 2
The Logos Framework: Temporally Relative Order and Residual Disorder in Finite Observations
Coskuner‐Weber, O., Alpsoy, S., Uversky, V. N., & Eyuboglu, S. (2026) · MetaScientia: Journal of the History and Philosophy of Science · doi:10.68469/ch2f0258
“They also contain poorly constrained regions where the model may generate plausible but unreliable outputs (Ji et al., 2023; Manning et al., 2020; Maynez et al., 2020).”
Extracting creativity from hallucination: Rethinking large language models
Jiang, X., Liu, Y., Shen, Y., Xu, C., Tian, Y., Chen, J., Zhai, X., Liu, Y., Hua, F., Zhao, B., et al. (2026) · AI Plus · doi:10.59717/ipj.aiplus.2026.100008
Allaf, F., & Özcan, M. (2026) · Diagnostics · doi:10.3390/diagnostics16193180
LLM-Supported Hybrid Reranking Architecture for Candidate-Job Matching in Recruitment Processes
Dursun, M., Doğan, B., & Canlı, H. (2026) · Celal Bayar Üniversitesi Fen Bilimleri Dergisi · doi:10.18466/cbayarfbe.1861278
Ponduru, P. S., Nandanavanam, P. P. V., & Ponduru, S. K. K. (2024) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrset2613385
A Tool-Augmented AI Agent for Grounded Access to European Cultural Heritage
Landolfi, P., Porcelli, F., Cioffi, S., Cuffa, L. D., Volpe, M., Nardo, E. D., & Ciaramella, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39385-2_3
Hayoune, K. (2026) · Islamic Reports · doi:10.66638/fsavt586 · Cited by 1
“The risk is that a model states falsehoods about the text, the law or the practice of Islam with unwarranted confidence (Ji et al., 2023), or reproduces distorted portrayals of Muslims (Abid et al., 2021).”
Janapamula, T. S. N. S., Peddi, A., RamaKrishna, B., Mandela, Y. N. L. D., & Balla, A. D. (2026) · International Conference on Innovation & Growth in Next-Gen Intelligent Technology & Engineering (IGNITE) · doi:10.1109/ignite69592.2026.11705956
“The generative models still suffer from hallucination problems which create false or unproven statements that especially affect knowledge-rich and domain-specific environments [3].”
DreamFold : A World Model to efficiently generate protein folding pathways in the latent space
Ianeselli, A., Im, J., Cavallin, E., & Gerstein, M. (2026) · Protein Science · doi:10.1002/pro.70794 · Cited by 5
Sajjad, M., Mirza, S. B., Sajjad, A., & Amer, R. (2026) · Cureus · doi:10.7759/cureus.117238
Dijital Çağda Çevirmenin Konumu ve Öne Çıkan Çeviri Edinçleri
Tumer, G. (2026) · Amasya Sosyal Bilimler Araştırmaları Dergisi · doi:10.70869/asbad.1986586
Large Language Models Create Hallucinations in Response to Negated Text
Seo, J., Moon, H., & Lim, H. (2026) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3849694
A Hybrid BDI + RAG Multi-Agent Architecture: Plan-Based Reasoning over Multimodal Retrieval
Yesil, H., Tezel, B. T., & Challenger, M. (2026) · Applied Sciences · doi:10.3390/app16199699
Wójcik, S., Rulkiewicz, A., Jarząbek, M., & Domienik‐Karłowicz, J. (2026) · doi:10.2196/preprints.113208
Vera, L., Craveiro, O., Malheiro, R., Dias, M., & Correia, R. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8100305
Barad, K., Gunjan, R., & Butalia, A. (2026) · International Conference on Innovation & Growth in Next-Gen Intelligent Technology & Engineering (IGNITE) · doi:10.1109/ignite69592.2026.11705780
“Chain-of-Thought prompting gets the model to break a problem into steps rather than jump straight to an answer, which surfaces logical gaps that would otherwise turn into hallucinations; a plain “think step-by-step” instruction measurably improves factuality on sensitive questions [10].”
InfluentialElena, Z., Ochotnicky, S., Fandáková, M., Levashenko, V., & Rabčan, J. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1882397
KBES for DfM and DfS of CNC Milled Parts: Requirements Analysis and Technology Blueprint
Kremer, G., Königs, M., & Stark, R. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-38598-7_4
Ross, M., & Amundson, J. (2026) · American Journal of Clinical Hypnosis · doi:10.1080/00029157.2026.2736088
Uso de la inteligencia artificial en la lectura crítica de artículos científicos médicos
Auza-Santiváñez, J. C., Torrico, B. A. L., Mamani-Limachi, R. M., & Vasquez, H. T. Q. (2026) · doi:10.62486/978-9915-9928-3-9.ch18
Enhancing Autonomous Agent Accuracy Through Reflection-Based Reasoning
Pang, L., Cen, C., Yu, J., Huang, D., & Sun, X. (2026) · International Conference on Advanced Network Technologies and Applications (APAN) · doi:10.1109/apan70967.2026.11709799
“Prior work argues that language models can produce fluent but ungrounded text because generation is driven by statistical regularities rather than grounded understanding [7], while hallucination remains a persistent limitation in natural language generation [8].”
Yang, Y., Li, J., Li, Y., Zhang, S., & Guo, K. (2026) · Computers in Human Behavior · doi:10.1016/j.chb.2026.109205
Liu, Y., Yan, L., & Ma, Z. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116530
Sethi, S., & Singh, S. (2026) · ACM Transactions on Social Computing · doi:10.1145/3849483
Martinez-Sanchis, S. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105321
CareFusion AI: Evidence-Based Agentic Intelligence for Multi-Modal Clinical Decision Support
Sujith, A., Gopan, A., Varghese, R., et al. (2026) · doi:10.1109/icscst70031.2026.11709822
“While LLMs enable conversational interfaces [6], they hallucinate unsupported information [7].”
Generative Discourse Parsing for Indian Law
Chaitra, C. R., Bhutani, N., Kulkarni, S., Sagi, S. R. A. V., Pandey, S., Yalavarthy, R., Chakraborty, D., & Upadhyay, P. (2026) · Artificial Intelligence and Law · doi:10.1007/s10506-026-09544-3
Pang, B., Zhang, J., Lai, J., & Nartey, B. (2026) · Automation in Construction · doi:10.1016/j.autcon.2026.107267
Xiao, Y. H., Nan, Y., Zhong, Z., Ye, M., & Zheng, Z. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3832105
AI Legal Chain Resolver: An Intelligent Sinhala Legal Assistant for Sri Lankan Commercial Law
Yogesh, R. J., Mapagedara, T. L. B., Vimukthi, Y., et al. (2026) · doi:10.1109/apan70967.2026.11709878
“No existing benchmark for Sinhala legal QA was available [4].”
InfluentialHalluChain: Measuring and Controlling Cascade Hallucination Propagation in Multi-Agent LLM Pipelines
Nair, A. M., Jacob, S. S., S, A. P., Jayakrishnan, A., Manoj, A., Nathan, S. V., H, A. D. T., & Pradeesh, N. (2026) · International Conference on Innovations in Mechanical, Robotics, Computing and Biomedical Engineering (ICIMRBE) · doi:10.1109/icimrbe70745.2026.11709899
Steering Tree-of-Thought Reasoning via Deductive Verification
Haoliang, C., Tang, E., Zhang, S., Mao, J., Fu, Y., Ma, J., Cui, K., Liu, Y., Tian, Y., Gao, X., et al. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3832200
Budiman, A. M., Verrell, C., Kristiawan, H. E., Chowanda, A., & Anderies (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715172
“There are also differences in the use of abbre-viations, slang, humor, and personal expression [6], [14].”
Lorensia, A., Vincent, D., Febrianto, D. R., Jabar, B. A., & Halim, R. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715110
“In this domain where risks are high and precision is absolutely required for patient safety; inaccuracies pose a big threat [2], [6].”
Kaur, D., Wijaya, L., Meng, C. K., Wagle, S., Wahono, J. W., & Sari, N. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715111
“Research has revealed that people have been worried about hallucinations, biased responses and factual inaccuracies in AI generated content [17, 18].”
A Reproducible Multimodal LLM-as-a-Judge Workflow for Exploring Epistemic Dissonance
Yuda, R. (2026) · Companion Publication of the International Conference on Multimodal Interaction (ICMI Companion) · doi:10.1145/3776591.3832521
“Nevertheless, their tendency to hallucinate causal links between random physiological noise and visual events remains a critical hurdle [13].”
H, S. F. T., Supangkat, S. H., & Anggara, D. W. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715122
DeMarco, R. M., Rodríguez, J., Hess, L., Cady, A., Chua, F. B., Cheng, D., & Mezzacappa, E. S. (2026) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/10711813261493609
LLM-powered clustering for entity resolution
Fu, J., Tang, H., Khan, A., Mehrotra, S., Ke, X., & Gao, Y. (2026) · The VLDB Journal · doi:10.1007/s00778-026-01006-1
“We refer to these errors as misclassi-fications , but the broader LLM literature formally classifies such factually contradictory outputs as intrinsic hallucinations [41].”
Guerschberg, L., & Gutierrez, Y. E. (2026) · Revista Multidisciplinar Epistemología de las Ciencias · doi:10.71112/gpqkd594
Türk, G. D. (2026) · Opus uluslararası toplum araştırmaları dergisi · doi:10.26466/opusjsr.1959141
A modular image-to-translation framework for Egyptian hieroglyphic images
Fuentes-Ferrer, R., Domingo, J. D., & Herrera, P. J. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116549
Karanam, S. A. K., Hartman, N. W., Tharmasanthiran, A., Milton, N., & Alexeenko, A. A. (2026) · Manufacturing Letters · doi:10.1016/j.mfglet.2026.08.069
Securing Agentic AI via Hybrid CNN–Transformer Detection and Cryptographic Intent Binding
Sindhu, N., Jagruthi, H., Pai, S., Chiranth, S., Aishvarya, V., & Pavan, J. (2026) · Algorithms for intelligent systems · doi:10.1007/978-3-032-25627-0_31
To what extent can Large Language Models support Life Cycle Assessment of manufacturing processes?
Trapani, M. G., Lorenzo, R. D., Fratini, L., & Ingarao, G. (2026) · Manufacturing Letters · doi:10.1016/j.mfglet.2026.08.090
FROM DATA TO ACTION: GENERATIVE AI FOR TACKLING VIOLENCE AGAINST WOMEN
Ruiz, O. G. D. A., Caires, A. R. L., de Nadai, R. D. L., et al. (2026) · Street Art & Urban Creativity · doi:10.66838/sauc.6433
Madaschi, F., Cassandro, J., & Trani, M. L. A. (2026) · Journal of Information Technology in Construction · doi:10.36680/j.itcon.2026.050
Bahi, A., & Ourici, A. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.101076
Conflict-aware uncertainty alignment for tool-augmented document-centric multimodal intelligence
Muthusami, R., & Saritha, K. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02409-3
“Ji et al. [25] categorize hallucinations into intrinsic hallucinations, which contradict source evidence, and extrinsic hallucinations, which introduce unsupported information beyond the available context.”
Technical–ethical–governance circuit–breaker framework for safe and sustainable AI governance
Yang, C.-C., Lai, Y.-T., Shia, B.-C., Selvamani, M. J. P., Lo, C.-Y., Chen, M. Y., & Liu, Y.-S. (2026) · Sustainable Futures · doi:10.1016/j.sftr.2026.102193
Living with Risk: Folk Theories of AI Hallucinations Among Young Chinese Users
Liu, H., & Zhang, Y. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2738104
The Illusion of Success: Procedure-Aware Evaluation is Critical for LLM Agents
Cao, H., Driouich, I., & Thomas, E. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37682-4_29 · Cited by 32
Alignment as an Institutional Problem
Berg, C. (2026) · Palgrave studies in classical liberalism · doi:10.1007/978-3-032-22310-4_7
Adaptive Claim Level Hallucination Detection and Mitigation for BlackBox LLMs on Amazon Bedrock
Katta, M. R. (2026) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic70896.2026.11717234
“Hallucination generating output that is factually wrong, internally inconsistent, or unsupported by available evidence is documented across model families and scales [1],[6],[21].”
Reframing Museum Intelligence: A Survey of Large Language Models in Museums
Bu, F., Li, Z., Jiang, Y., & Liu, Z. (2026) · Journal on Computing and Cultural Heritage · doi:10.1145/3856306 · Cited by 2
Editing by prompt. How professional editors use ChatGPT when revising business texts
Janssen, D., & IJlst, D. (2026) · Computers & composition/Computers and composition · doi:10.1016/j.compcom.2026.103038
Collapse or creativity - Hallucinations in recursive synthetic data generationPreprint
Vallevik, V. B., Babić, A., Edwin, B., Befring, A. K., & Nygård, J. F. (2026) · Research Square · doi:10.21203/rs.3.rs-10883391/v1
Shen, L.-J. (2026) · Communication Methods and Measures · doi:10.1080/19312458.2026.2742796
Fatima, S. S., Reddy, B. B., Ramadevi, N., Venkat, N., Imran, S., & Sameer, S. M. (2026) · International Conference on Soft Computing for Security Applications (ICSCSA) · doi:10.1109/icscsa69367.2026.11707969
“Researchers conducted a study concerning the phenomenon of hallucination in content produced by LLMs, and they found that retrieval grounding is one effective way to rectify inconsistencies in the information presented [14].”
Two-Stage Collaborative Reasoning for Knowledge Graph Question Answering in Additive Manufacturing
Dong, X., Li, S., Wei, J., Zhou, J., & Yan, C.-B. (2026) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case69030.2026.11704151
“Ji et al. [7] surveyed this phenomenon, showing that inconsistencies between generated content and factual data remain a key challenge for real-world reliability.”
Bashir, A., & Peng, R. (2026) · Data & Knowledge Engineering · doi:10.1016/j.datak.2026.102656
Sain, N., Nawi, S. M., Yusof, S. M., & Kamaludin, P. N. H. (2026) · International Conference on Artificial Intelligence and Data Sciences (AiDAS) · doi:10.1109/aidas71914.2026.11712589
“A major challenge in human–AI collaboration involves managing system limitations, particularly the risk of AI hallucinations, where LLMs produce factually inaccurate information or fabricated references [16].”
Li, K., Pan, Y., Yi, Z., Guo, S., Liu, P., Dong, L., Wang, L., Wang, Y., Qin, W., Cheng, X., et al. (2026) · Earth Science Informatics · doi:10.1007/s12145-026-02258-9
Tian, Z., Cao, X., Ma, X., & Dong, Y. (2026) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case69030.2026.11704252
Prasad, R., Shyalika, C., Pawar, A., Rathod, A., Sheth, A., & Amit, S. (2026) · IEEE Intelligent Systems · doi:10.1109/mis.2026.3721785
Tabuchi, H., Oshika, T., Akada, M., Toba, Y., & Gomi, F. (2026) · AJO International · doi:10.1016/j.ajoint.2026.100328
Structure-Constrained Knowledge Reasoning for Manufacturing Process Planning Support
Feng, X., & Peihan, W. (2026) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case69030.2026.11704283
“Because knowledge is stored implicitly in parameters, LLMs may fail to retrieve precise process details, producing hallucinations that violate engineering logic [8].”
Contrastive hallucination impact mitigation and evaluation for zero-shot dense retrieval systems
Ge, X.-Y., & Xu, G.-L. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02892-1
“Hallucinations in LLMs—factual inaccuracies and irrelevant content [14, 15]—pose critical challenges for retrieval.”
Jeon, J., Sivakumar, K., Athaide, G. A., & Raj, S. P. (2026) · Technovation · doi:10.1016/j.technovation.2026.103735
Feng, X., Huang, Y., Yang, Y., Peng, Z., Leng, Y., & Zang, H. (2026) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb71176.2026.11716376
“An existing review of natural language generation illusions points out that inconsistencies between model output and evidence weaken credibility in professional applications [4].”
Hirahata, Y., & Sakahira, F. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02075-5
“Research on abstractive summarization and natural language generation has repeatedly pointed to hallucination, in which a generative model produces content not present in the input, as well as a lack of faithfulness to the input information [19, 20].”
Chen, L., Liu, C., & Shin, W.-J. (2026) · Frontiers in Marine Science · doi:10.3389/fmars.2026.1944839
GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference
Wu, H., Zhou, S., 张宏新, et al. (2026) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case69030.2026.11704481
“However, as a probabilistic knowledge source, the LLM’s logical hallucinations, output variance, and overconfidence [26] make generated judgment matrices unlikely to satisfy AHP’s consistency requirement ( CR ≤ 0 .”
Effective Context Management for LLM Agents via Hybrid Chat History Optimization
Songa, S., Bayyavarapu, S. R. K. V., Gulkotwar, N., Pasupuleti, V., Allala, S. R., & Tyagi, S. (2026) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic70896.2026.11717333
Durante, G. E. (2026) · Qeios · doi:10.32388/t420iv.4
FinScale: Adaptive Test-Time Scaling for LLM-Based Multimodal Financial Data Analytics
Yin, B., Liu, Y., & Zhang, B. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5696-9_24
Comparing large language models and prompting techniques to control an embodied persuasive coach
Corrò, C., & Chittaro, L. (2026) · Behaviour and Information Technology · doi:10.1080/0144929x.2026.2742725
Wang, X. (2026) · International Conference on Artificial Intelligence, Digital Media and Education · doi:10.1145/3839592.3839722
“The above perspectives argue that it is not possible for human language features to be used for distinguishing human-written text from AI-generated text, since both use statistical models for text generation and detection (Ji et al., 2023) [6].”
Ge, H., Shi, Z., & Nie, Y. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-5712-6_34
Claim level graph reasoning for training free LLM hallucination mitigation
Wang, H., & Zhao, W. (2026) · Discover Computing · doi:10.1007/s10791-026-10667-z
“LLMs may generate statements that are fluent and plausible but factually incorrect, unsupported by evidence, or inconsistent with external knowledge [1, 2].”
Cultural and multimodal realization in various AI models: text to image, image to text
Albawardi, A., & Olwi, A. (2026) · Frontiers in Communication · doi:10.3389/fcomm.2026.1959385
Generative AI as a social partner for young adults: Dual pathways to resilience and AI dependence
Shin, Y., Jeong, D., Kang, H. C., & Lee, S. W. (2026) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2026.103141
Nie, Y., Shi, Z., & Ge, H. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-5712-6_24
From Tool Dependency to Critical Synergy: A Multi-Agent Collaborative Framework for AI Literacy
Pan, S., Chen, X., & Zhang, L. (2026) · International Conference on Artificial Intelligence, Digital Media and Education · doi:10.1145/3839592.3839717
“The system optimizes complex tasks by deploying three agents with distinct logical protocols: RAG-based Tutoring Agent: To mitigate “hallucinations” [ 8 ] , this agent employs a Retrieval-Augmented Generation mechanism [ 9 ] .”
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.




