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 4,001–4,100 of 4,839
Query-Aware Context Selection for Retrieval-Augmented Generation
Iratni, M., Boughanem, M., & Dkaki, T. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809959
Numerical Hallucinations in Retrieval-Augmented Generation: Detection and Analysis
Roy, S. S. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809882
SmartSearch: Process Reward-Guided Query Refinement for Search Agents
Wen, T., Dong, G., & Dou, Z. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809700 · Cited by 18
Semantic degradation of scientific text in AI editing
Semiletova, A. N. (2026) · Language and Text · doi:10.17759/langt.2026130216
Hallucinations in LLMs: a lifecycle-based survey of causes, detection, mitigation, and prevention
Lamba, N., Tiwari, S., & Gaur, M. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01214-6 · Cited by 1
“The framework identifies the shortcomings in the existing data collections and underscores the necessity of multi-dimensional benchmarks to facilitate layer-wise diagnoses, chain-of-thought verification and domain-specific hallucination monitoring [12, 13].”
InfluentialOnline safety by design: towards user-centric development of safer AI-based systems
Baldwin-McDonald, T., Fard, A., Fletcher, D., Gutmann, A., & Su, Q. (2026) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2025.0126 · Cited by 1
Lorusso, R., Maci, A., & Coscia, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-25029-2_11
AI Hallucination as Epistemic Proliferation
Karunanayaka, I. P. (2026) · Journal of Ethics and Emerging Technologies · doi:10.55613/jeet.v36i2.238
Zhang, X., Nie, X., Liu, Y., & Wang, Z. (2026) · Mathematics · doi:10.3390/math14142562
An Investigation of Hallucination Phenomena in Indian Low-Resource Language
Baghel, P., Yadav, R., & Kumar, N. (2026) · International Conference on Secure Cyber Computing and Communications (ICSCCC) · doi:10.1109/icsccc69031.2026.11600243
“It is when a model generates outputs that can be quite misleading, illogical, and incorrect [1], [2].”
Kremer, P. A., Chern, W., Günay, E. E., Günay, A., Kremer, G. E. O., Haapala, K. R., & Kim, K.-Y. (2026) · Lecture notes in mechanical engineering · doi:10.1007/978-3-032-22784-3_1
Grohol, J. M. (2026) · Journal of Participatory Medicine · doi:10.2196/95153 · Cited by 1
“That is, a model can produce confident, well-structured, and completely fabricated clinical guidance with equanimity [5].”
InfluentialASLAN, O. (2026) · Cumhuriyet International Journal of Education · doi:10.30703/cije.1863305
GenAI vs Traditional AI: A Comparative Framework Across Five Domains
Khanna, S., Yadav, A., & Kapoor, K. (2026) · IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS) · doi:10.1109/i2cacis69435.2026.11600276
“Rather than operating as isolated predictors, agents use working memory and external tools (e.g., APIs or code interpreters) to autonomously carry out complex multi-step workflows in dynamic environments [6],[7],[11].”
Trustworthiness in AI: on SciCompBot—the scientific computing chatbot
Hansen, A. C., & Circelli, F. (2026) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2025.0116 · Cited by 1
From Linear to Recursive: Orchestrating Self-Correcting Enterprise Agents with N8n
Salaheldin, F. M., Metwally, S. A., Ali, R. E., & Mansour, H. A. H. (2026) · IEEE International Conference on Smart Sustainable Systems for Computer and Engineering Applications (3SCEA) · doi:10.1109/3scea68071.2026.11603103
“If the retrieval stage misses a critical detail such as an employee ID or policy condition the generation stage is likely fail or invent false information” [4], [6].”
Retrieval-augmented clinical decision support for structured hip-joint disease assessment
Long, Q.-Y., Wang, G. Q., & Yang, W.-L. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1890014
“Medical large language models can organize clinical text, but their outputs require grounding, evaluation, and governance because unsupported generation remains a recognized concern (27– 32).”
Świgoń, M. (2025) · Zagadnienia Informacji Naukowej - Studia Informacyjne · doi:10.36702/zin2024.02.07 · Cited by 2
Balachandra, V., Islam, S., & Hossain, M. T. (2026) · International Conference on Smart Communications and Networking · doi:10.1109/smartnets69662.2026.11604821
“However, LLMs exhibit fundamental limitations such as hallucinations that generate inaccurate information [4], [5] and information leakage where sensitive data can be extracted through crafted prompts [6], [7].”
Kumar, R., Khullar, S., & Arora, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0368-8.ch003
From QA to Execution: Building an Action-Oriented AI Agent for Corporate Support
Salaheldin, F. M., Metwally, S. A., Ali, R. E., & Mansour, H. A. H. (2026) · IEEE International Conference on Smart Sustainable Systems for Computer and Engineering Applications (3SCEA) · doi:10.1109/3scea68071.2026.11603036
“Without real-time access to internal data, generic or hallucinated responses are often generated [4], [5].”
SAT-Based Synthesis and DEVS Simulation from Partial Generative Specifications for Verifiable AI
Alshareef, A., & Zeigler, B. P. (2026) · Logics · doi:10.3390/logics4030007
“Some researchers frame these issues as a form of hallucination attributed to a variety of contributing factors [1].”
Santhosh, S., & Jennifer, G. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1892734
Evidence-grounded generative daily reporting for activated sludge operation
Zhao, L., Tian, Z., Gao, Z., et al. (2026) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2026.110473
Bellaarabi, E. M. (2026) · European Journal of Contemporary Education and E-Learning · doi:10.59324/ejceel.2026.4(4).12
Explainable GraphRAG: A Path-Based Interpretability Framework for Ontology-Grounded Clinical LLMs
Ali, M., Fayed, Z. T., & Mabrouk, M. (2026) · IEEE International Conference on Smart Sustainable Systems for Computer and Engineering Applications (3SCEA) · doi:10.1109/3scea68071.2026.11603104
Preventing Wrong Work Item Retrieval in LLM-Based MCP Systems Through Multi-Agent Validation
Gökbulut, B. (2026) · Cognitive Models and Artificial Intelligence Conference (AICCONF) · doi:10.1109/aicconf69182.2026.11600651
“LLM hallucinations—plausible but incorrect outputs— have been extensively studied [6], with mitigations including retrieval-augmented generation (RAG) [3] and chain-of-thought prompting [7].”
Włodarski, R. (2026) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3803437.3805783
A Cost-Sensitive Three-Way Routing Framework for Edge-Cloud LLMs
Zhao, P., Huang, D., Zhang, Q., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3557-5_17
Coordinated Deception: Generative Agents for Multi-Agent Fake News Generation
Orlando, G. M., Russo, D., Gatta, V. L., & Moscato, V. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3831690
“Likewise, state‑of‑the‑art language models frequently produce “hallucinations” – fluent text that is factually incorrect or misleading [38].”
MoRE-RAG: Bayesian optimal fusion of multiple retrieval experts for retrieval-augmented generation
Xu, J., Li, X., Song, Q., & Zhu, S. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134536 · Cited by 2
Chen, F., Yang, G., Lee, C., Jie, Z., & Chen, Y. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3831589
Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains
Sigloch, P., & Benzmüller, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-32335-4_30 · Cited by 1
Gérard Biau, A., & Boyer, C. (2026) · Statistics & Probability Letters · doi:10.1016/j.spl.2026.110899
“Modern language models (LMs) can hallucinate, producing outputs that sound convincing but are factually wrong [Ji, Lee, Frieske, Yu, et al., 2023, Kalai and Vempala, 2024].”
LLM-RAG Intent Translation Meets Dual Time Scale Control for QoS-Guaranteed Video Services
Zhang, M., Guo, L., Chen, D., Yan, Y., Zhuang, Z., Qi, Q., Sun, H., Li, M., Zhou, C., Lu, L., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3557-5_16
Shi, Y., Liu, C., & Yu, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3378-6_38
Uncertainty-aware prediction of thermal expansion in complex oxides via LLM-curated literature data
Marshall, J., Alexander, M., García, V. J., Safin, J., Sanchez, S. L., Foadian, E., Rawn, C. J., Page, K. L., Kalinin, S. V., & Ahmadi, M. (2026) · APL Machine Learning · doi:10.1063/5.0333166
Yang, M., Ren, Y., Wang, H. B., Hou, W. Z., Li, W., Chun, Z., Zheng, W., & Ren, D. G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3426-4_5
Vaidya, V., Patwardhan, A., Das, S., & Kundu, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-33260-8_16
Ghazouani, A., Ayadi, M. G., & Achour, H. (2026) · 2026 Intelligence in Business and Industry (IBI) · doi:10.1109/ibi68858.2026.11604064
“Studies indicate hallucination rates vary by task, ranging from 8-15% for large models on constrained tasks to 15-25% for smaller models on open-ended medical question answering [43].”
S, S. F. H., Joby, N. J., & Soni, P. (2026) · doi:10.1109/icati69399.2026.11604377
“Recent studies on hallucination behavior [8], [9], [12] and benchmarks such as TruthfulQA [13] highlight the prevalence of factual inconsistencies in LLM outputs and the need for reliable verification mechanisms.”
Yılmaz, H. Ö., Duman, E., & Şahin, K. (2026) · Journal of Nutrition · doi:10.1016/j.tjnut.2026.101739
Ennaceur, I., Elghazel, H., Aussem, A., Lefebvre, G., & Sonnati, M. O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-32643-0_10
Data Augmentation for Fake Review Detection Based on Large Language Model with Multi-stage Prompting
Li, Q., Chen, J., & Zhang, W. (2026) · Journal of Systems Science and Systems Engineering · doi:10.1007/s11518-026-5731-y
Arabameri, F., Ploennigs, J., Imani, M., & Spyridis, P. (2026) · Infrastructures · doi:10.3390/infrastructures11070247
From Prediction to Policy: An Agentic AI Framework for Telecom Churn with XAI-Driven Validation
Bas, S. (2026) · International Balkan Conference on Communications and Networking (BalkanCom) · doi:10.1109/balkancom71095.2026.11605046
“SHAP [6] and Anchor [7] serve as complementary global and local validators, directly countering the hallucination risk documented in [18].”
A Road Map for Tamed Interactions with Large Language Models
Scotti, V., Keim, J., Hey, T., Metzger, A., Koziolek, A., & Mirandola, R. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3832776 · Cited by 2
Toward an internal moral purpose like normative governance function in artificial agency
Keleş, S. (2026) · AI and Ethics · doi:10.1007/s43681-026-01268-z
Yang, L., Wang, X., Yu, J., & Cao, Y. (2026) · Electronics · doi:10.3390/electronics15143191
CCR: Concept-centric reasoning for iterative query expansion in biomedical information retrieval
Zhou, C., Fan, R., Liu, Y., Bai, X., Tu, X., & He, T. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134543
Die KI-Achse: Allgemeine und modellabhängige Fehlermuster
Elsharkawy, A. E. (2026) · Essentials · doi:10.1007/978-3-662-74123-8_5
Cai, X., Pang, H., & Yu, Z. (2026) · AI Agent · doi:10.20517/aiagent.2026.28
Gengji, J., & Fu, Y. N. (2026) · iPharma · doi:10.1016/j.iphar.2026.100005
ClariCheck: Flagging Unsupported Inferences in AI-Generated User Propositions
Sharma, A., & Yadati, D. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816282
Retrieval-Augmented Generation Based Framework for Automated RFP Response Generation
Jamal, S., George, N. J., Menon, R. R., Niranjana, N., & Muhammed, P. A. A. (2026) · International Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS) · doi:10.1109/ic3sis69949.2026.11608289
“Existing work on LLMs and RAG primarily focuses on general applications and does not fully address enterprise specific requirements such as traceability, and compliance validation [6], [7].”
Linguistic Uncertainty Markers for Trust Calibration in AI-Assisted Decision-Making
Spillner, L., Rockstroh, J., Wenig, N., Zargham, N., Kiefner, L., Porzel, R., & Malaka, R. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816231 · Cited by 1
Tabuchi, H., Tanabe, M., Kihara, K., Moriguchi, T., & Gomi, F. (2026) · SN Comprehensive Clinical Medicine · doi:10.1007/s42399-026-02549-8
Perera, K. J. P. G., Nanayakkara, S., & Huff, E. W. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816225
Yu, P., Chen, X., & Wu, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37664-0_34
Mai, H., Li, W., Chen, J., Huang, B., Li, B., & Long, S. (2026) · International Conference on Computer and Multimedia Technology (ICCMT) · doi:10.1109/iccmt69755.2026.11608235
“Existing research defines hallucination as the phenomenon where generated content is inconsistent with facts, evidence, or input sources, and points out that it is prevalent in natural language generation tasks [1].”
Benchmarking Large Language Models on Long-Tail Plant Taxonomic Knowledge with PTTB-600
He, J., Xiao, J., Qu, H., & Xie, L. (2026) · Diversity · doi:10.3390/d18090541
Singh, M. (2026) · Transformation in Higher Education · doi:10.4102/the.v11i0.775
Fu, Q., Wu, R., Xu, D., & Zhang, J. (2026) · International Conference on Algorithms, Software Engineering and Network Security (ASENS) · doi:10.1109/asens69964.2026.11605265
“Although introducing LLMs enhances text processing, it introduces hallucination risks [8].”
Large language model-driven automated design and adaptive optimization of sliding mode controllers
Zhang, J., Wu, Y., Gao, S., et al. (2026) · Applied Mathematical Modelling · doi:10.1016/j.apm.2026.117204
Miličević, M., Rovis, M., Karlović, R., Šegota, S. B., Mrzljak, V., Lorencin, I., & Etinger, D. (2026) · Information · doi:10.3390/info17070706
Delaflor, M., & Toxtli, C. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816233
Mala, C. S., Gezici, G., & Giannotti, F. (2026) · Machine Learning · doi:10.1007/s10994-026-07121-y · Cited by 2
“Recent surveys (Huang et al., 2023; Ji et al., 2023; Zhang et al., 2025b ) offer comprehen - sive taxonomies and emphasize the persistent challenge of hallucinations in knowledge-intensive tasks, detailing definitions, causes, evaluation protocols, and mitigation strategies, with particular…”
Human and AI judgements of restorative responses to sexual abuse: The role of perceived severity
Peleg‐Koriat, I., & Asraf, K. (2026) · Legal and Criminological Psychology · doi:10.1111/lcrp.70053
Cross-Modal Misalignment as a Systemic Vulnerability in MLLMs
Angelis, V. D., Annunziata, D., Izzo, S., Giampaolo, F., & Piccialli, F. (2026) · International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) · doi:10.1109/mlise70044.2026.11607572
“In the domain of hallucination, existing frameworks typically categorize errors based on their semantic nature, distinguishing between object, attribute, and relation hallucinations [9], [10], or between intrinsic and extrinsic unfaithful-ness [11].”
Hybrid AI-Architecture for Vygotskyan Scaffolding: Mitigating Hallucinations in Rule-Based CALL
Brückner, M., & Tarat, S. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-33997-3_5
RAG-Enhanced Explainable AI for Regulatory-Compliant Credit Risk Assessment
Goyal, A., Pendyala, J. P., Sondagar, J., Jiang, S., & Shah, P. M. (2026) · IEEE International Conference on AI and Data Analytics (ICAD) · doi:10.1109/icad69378.2026.11609194
Majid, Z., Chaudhuri, W., & Kanabar, V. (2026) · IEEE International Conference on AI and Data Analytics (ICAD) · doi:10.1109/icad69378.2026.11608853
“Mc denotes the perceived confidence of the AI output, which frequently appears misleadingly high [14].”
Tewari, V., Alawi, D. A. S. A., Shaik, M. V., & Morandé, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-8964-6.ch008
Human Autonomy and Forms of Vulnerability in Automated Contracting
Ballell, T. R. D. L. H. (2025) · Springer eBooks · doi:10.1007/978-3-031-93247-2_4
Chen, C., Chen, W., Dong, M., & Cai, L. (2026) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3829374
Čižinská, R., & Neset, P. (2026) · Proceedings of the ... International Conference on Business Excellence · doi:10.2478/picbe-2026-0046
“Another risk relates to hallucinations, that is, situations where an LLM generates factually incorrect or source-unsupported content while remaining linguistically persuasive (Ji et al., 2023).”
Retrieval Augmented Generation Enhanced RLHF Framework for Factuality Verification Improvement
Zhou, X. (2025) · International Conference on Intelligent Decision-making and Machine Learning (ICIDML) · doi:10.1109/icidml69845.2025.00022
“Hallucination phenomena in neural text generation have been systematically reviewed [1], categorizing them into intrinsic hallucinations (generated content contradicts source content) and extrinsic hallucinations (generated content cannot be verified from source content).”
Logical Misconceptions, Pragmatic Insufficiencies in LLMs and How to Fix Them
Asher, N. M., & Bhar, S. (2026) · Topoi · doi:10.1007/s11245-026-10459-6
Maghsoodi, A. I., Kurz, J., Lawrenson, R. A., Parsons, M. J. G., Walker, C. G., O’Sullivan, M., & Rouse, P. (2026) · Health Policy and Technology · doi:10.1016/j.hlpt.2026.101292
Lebakeng, T. (2026) · Image & Text · doi:10.17159/2617-3255/2026/n40a7
Morales, C. (2026) · Education Sciences · doi:10.3390/educsci16081179 · Cited by 2
“Generative AI can produce responses that are plausible but inaccurate or incomplete (Ji et al., 2023).”
Closed-loop agentic AI in drug discovery
Chhetri, P. (2026) · RSC Medicinal Chemistry · doi:10.1039/d6md00319b · Cited by 4
Per una psicopatologia dell'Alterità artificiale
Grossi, A. (2026) · RIVISTA SPERIMENTALE DI FRENIATRIA · doi:10.3280/rsf2026-002007
Fishing for AI use in science education using modern knowledge of fishes
Schumacher, G. T., Murphy, C. A., & Kinnison, M. T. (2026) · Fisheries · doi:10.1093/fshmag/vuag044
Why parents of children aged 4–6 use generative AI: a qualitative interview study
Güngör, B. Ş., & Güngör, A. (2026) · Children and Youth Services Review · doi:10.1016/j.childyouth.2026.109196
Capability Degradation in Small Language Models Under Low-Signal Data Corruption
Qamar, R., Appasani, B., Bizon, N., Verma, S., & Jha, A. V. (2026) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai69016.2026.11613657
Purk, J. (2026) · Logistics Research · doi:10.1108/lore-12-2025-0184 · Cited by 1
Dinçer, F. A., & Kilimci, Z. H. (2026) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai69016.2026.11613709
“However, standalone LLMs remain susceptible to hallucinations and may generate factually inconsistent responses in 979-8-3315-5818-5/26/$31.00 © 2026 IEEE domain-specific settings [4].”
InfluentialStructure-aware consistent graph autoencoder for generative content review
Zhang, H., Liu, C., Zhang, L., Wang, Z., Yang, Z., & Chen, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134261
Hallucinations in Structured Extraction: A Case Study on Prompt-Based Semantic Role Labeling
Kazlaris, I., Diamantaras, K., Antoniou, E. N., & Bratsas, C. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8090270
“We analyze such hallucinations through the lens of rule grounding, extending the broader view of hallucination as unfaithful or insufficiently grounded generation [14].”
Diagnosing RAG vulnerabilities via sensitive knowledge recognition
Liu, Z., Liu, J., Lyu, X., Dai, J., Hu, F., Wang, B., Zhang, J., & Wang, W. H. (2026) · Pattern Recognition Letters · doi:10.1016/j.patrec.2026.04.037
Cao, L., Chau, K. T., & Yahaya, W. A. J. W. (2026) · Journal of Educational Computing Research · doi:10.1177/07356331261469058
Wei, S., Liu, X. D., & Shi, Y. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105085 · Cited by 1
Rivas, P., & Liang, Z. (2026) · AI · doi:10.3390/ai7080281 · Cited by 1
Pant, Y. R., Adarbah, H. Y., Noore, A., Che, D., Ahmed, A., & Ayala, R. (2026) · AI · doi:10.3390/ai7080280
“Beyond the “hallucination of completeness” observed in Category 4, where the model https://doi.org/10.3390/ai7080280 credits missing intermediate steps for concise responses [40], instructor feedback revealed critical “Failed Arithmetic Verification” and “False Logic Flagging” issues.”
InfluentialLi, A., Yao, S.-T., Chen, B.-X., Li, X. X., & Guo, S.-Y. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1909370
“First, LLMs are prone to generating factually incorrect or clinically misleading content, a phenomenon often referred to as hallucination, which in the context of depression psychoeducation could inadvertently reinforce maladaptive beliefs or provide unsafe advice (21).”
Wu, J., Gan, L., Zhang, X., & Shu, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7193839
Mun, J., Kim, N., & Choi, J. (2026) · Electronics · doi:10.3390/electronics15153307 · Cited by 1
Palermi, S., Saglietto, A., D’Ascenzo, F., Ferrari, G. M. D., Bruno, F., Tse, G., Kizilkilic, S. E., Tjong, F. V. Y., Ruipérez-Campillo, S., Keser, N., et al. (2026) · Progress in Cardiovascular Diseases · doi:10.1016/j.pcad.2026.07.005 · Cited by 2
Constraint-aware specialized large language models for RF circuit reasoning
Chen, J., Liu, J., Wang, Y.-X., et al. (2026) · Microelectronics Journal · doi:10.1016/j.mejo.2026.107404
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.




