Survey of Hallucination in Natural Language Generation
Open accessThe DOI matches its Crossref record; 355 of the 360 references it cites were found in a registry or an index, and 4 are not checked yet; 224 of the 256 sources its claims cite were checked for support.
Abstract
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.
Verified 2026-11-19 · 4 references not checked yet
Overview
CoChat Summary
TL;DR
This survey provides a broad overview of hallucination in natural language generation, covering definitions, contributors, metrics, mitigation methods, and task-specific progress across summarization, dialogue, GQA, data-to-text, machine translation, vision-language generation, and LLMs. It distinguishes intrinsic from extrinsic hallucination and argues that hallucination must be treated differently across tasks and sources.
Key findings
- The survey categorizes hallucination into intrinsic hallucination, where generated output contradicts the source, and extrinsic hallucination, where output cannot be verified from the source; extrinsic hallucination is not always erroneous because it may come from factually correct external information.
- It reports prevalence examples from cited work: 25% of summaries generated by state-of-the-art abstractive summarization systems have hallucinated content; 62% of first sentences in WIKIBIO have additional information not stated in the corresponding infobox; and 74% of samples in the QMSum dataset consist of inconsistent facts.
- It reviews hallucination metrics as statistical, model-based (IE-based, QA-based, NLI-based, faithfulness classification, LM-based), and human evaluation, and mitigation methods as data-related and modeling/inference methods including architecture changes, planning/sketching, RL, multi-task learning, controllable generation, and post-processing.
- For LLMs, it notes that RLHF reduced the hallucination rate from 41% to 21% in closed-domain tasks for InstructGPT, and discusses reference-dependent and reference-free hallucination metrics plus mitigation via data refinement, RAG, safety fine-tuning, model editing, decoding methods, chain-of-thought variants, post-processing, and ensembling.
Methods
- Literature survey design: the paper reviews existing research on hallucination in NLG rather than conducting new experiments or primary data collection.
- Coverage: general NLG hallucination topics (definitions, contributors, metrics, mitigation, future directions) plus task-specific sections on abstractive summarization, dialogue generation, generative question answering, data-to-text generation, neural machine translation, vision-language generation, and large language models.
- Analysis: synthesizes and compares definitions, metrics, mitigation approaches, and future directions across tasks, with examples in tables and figures; the LLM section was updated in Jan 2024.
Limitations
- The paper states that GQA has no standard definition or categorization of hallucination and no automatic metric specifically for hallucination in GQA; it also notes that open-domain dialogue lacks a standard hallucination metric and that VL hallucination research is still in its early stage.
- The paper states that extrinsic hallucination has been somewhat overlooked and is more challenging to reduce, and that most existing mitigation methods do not distinguish between intrinsic and extrinsic hallucination.
- Evident from the text: as a survey, it does not provide new empirical validation of metrics or mitigation methods, and its LLM coverage is explicitly updated only through Jan 2024, so later work is not included.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
124 Valid · 26 Not valid · 19 Not checked · 135 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Furthermore, perturbation, where the insertions of most common tokens are placed at the beginning of the sentence, seems to be the most successful in hallucination mitigation.”
What the sources say
- Not checked — no full text of the sourcecites [133] [133] Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, and David Sussillo. 2019. Hallucinations in Neural Machine Translation. ICLR (2019). -
- Disputedcites [215] [215] Vikas Raunak, Arul Menezes, and Marcin Junczys-Dowmunt. 2021. The Curious Case of Hallucinations in Neural Machine Translation. (4 2021), 1172-1183. https://arxiv.org/abs/2104.06683v1 - sourceExperimental — accuracy not yet measured
In the passage describing the perturbation procedure (page unavailable), the paper says that inserting common tokens at the beginning is used to generate hallucinations, not mitigate them. Its prevention section instead discusses approaches such as robust learning and corpus-level filtering. (LLM, conf=0.92)
Checked by a reasoning model — may be wrong.
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“While there are works on the visual extension of faithfulness-oriented RLHF [303], these essentially involve labeling more data, which is expensive and difficult to scale.”
What the sources say
- Disputedcites [303] [303] Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and Tat-Seng Chua. 2023. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback. CoRR abs/2312.00849 (2023). https://doi.org/10.48550/ARXIV.2312.00849 arXiv:2312.00849 - sourceExperimental — accuracy not yet measured
RLHF-V does use human annotation for visual-model alignment, but it makes the contrary point about needing more labeled data. The Fine-grained Correctional Human Preference Collection section says its corrections improve data efficiency, and Section 4.3 reports comparable hallucination rates using only 200 preference examples versus an order of magnitude more ranking-labeled examples. Our copy does not establish a separate claim about annotation cost or scalability. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“Nevertheless, as illustrated by Falke et al. [66], off-the-shelf NLI models tend to transfer poorly to the abstractive summarization task.”
What the sources say
- Supportedcites [66] [66] Tobias Falke, Leonardo FR Ribeiro, Prasetya Ajie Utama, Ido Dagan, and Iryna Gurevych. 2019. Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . 2214-2220. - source
The Introduction states that models trained on NLI datasets transfer poorly to the paper’s downstream task of ranking generated summaries by correctness. The Conclusions likewise say that out-of-the-box NLI models do not perform well on that task. (LLM, conf=0.94)
- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Such wrong association results in generation with facts mixed up between two similar entities [60, 233].”
What the sources say
- Partly supportedcites [60] [60] Nouha Dziri, Andrea Madotto, Osmar Zaiane, and Avishek Joey Bose. 2021. Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding. EMNLP (2021). - sourceExperimental — accuracy not yet measured
The GPT2-KG passage describes an incorrect association between entities, and G Error Analysis gives an example of a generated response assigning a book to the wrong author. These support the claim that facts can be mixed up, but the paper does not say the entities involved are similar. The supplied passages do not provide page numbers. (LLM, conf=0.83)
- Supportedcites [233] [233] Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. EMNLP (2021). - source
The Introduction states that language models often mix up facts between two similar entities when generating factually incorrect statements. This directly supports the cited description of the resulting error. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“As a result, the target reference may contain information that cannot be supported by the source [198, 268].”
What the sources say
- Supportedcites [198] [198] Ankur Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, and Dipanjan Das. 2020. ToTTo: A Controlled Table-To-Text Generation Dataset. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . 1173-1186. - source
The Dataset section says that reference targets selected from web sentences may contain information that cannot be inferred from the source. The Data Annotation Process section also describes deleting phrases unsupported by table cells. (LLM, conf=0.93)
- Supportedcites [268] [268] Hongmin Wang. 2019. Revisiting Challenges in Data-to-Text Generation with Fact Grounding. In Proceedings of the 12th International Conference on Natural Language Generation . 311-322. - source
The Introduction reports that about 40% of human-written game-summary content cannot be directly mapped to the input boxscore records and draws on information beyond those inputs. Section 2.1 likewise describes reference content not licensed by the boxscore table. This supports the claim that a target reference may contain information the source does not support. (LLM, conf=0.93)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
117 more claims · 74 with their cited sources checked
Create a free account to see all 304 claims and to verify the 2 references still open.
- Borderline: one of the tests for a substantial claim is unclear. 1
- It may state two separate claims as one. 90
- Probably not a substantial claim. 142
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Hallucination can lead to serious consequences such as incorrect or misleading code, security risks, and ethical issues [186].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [186]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“citation fabrication constitutes a form of extrinsic hallucination in the absence of retrieval augmentation, since the model generates references not grounded in any provided source material [4].”
From How LLMs Cite and Why It Matters: A Cross-Model Audit of Reference Fabrication in AI-Assisted Academic Writing and Methods to Detect Phantom Citations (2026) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent taxonomic work distinguishes at least seven cases [15,18].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“LLMs struggle to generate accurate and up-to-date responses on current topics, due to outdated knowledge, lack of domain-specific expertise, or hallucination13–17.”
From Leveraging long context in retrieval augmented language models for medical question answering (2025) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fine-tuning can enrich LLMs with domain knowledge, enhance their specific ability, improve the fairness and reliability of the outputs, and prevent certain damage caused by hallucination [26].”
From FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning (2024) · cites this paper as [26]
Experimental — accuracy not yet measured
41 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Extrinsic Object Hallucination
“CHAIR (Caption Hallucination Assessment with Image Relevance) metric, which calculates what proportion of object words generated are actually in the image according to the ground truth captions.”
§ Extrinsic Object Hallucination
“CHAIR 𝑖 measures per-instance object hallucination, i.e. what fraction of object instances in each generated caption are hallucinated.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 7.1 Hallucination Definition in Abstractive Summarization
“For instance, in Table 1, given the input article shown in the caption, an example of intrinsic hallucination is ' The Ebola vaccine was rejected by the FDA in 2019, '”
§ 2.1 Categorization
“in the abstractive summarization task from Table 1, the generated summary ' The first Ebola vaccine was approved in 2021 ' contradicts the source content”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Survey of Hallucination in Natural Language Generation
“The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation; and (3) hallucinations in large language models (LLMs)”
§ 1 INTRODUCTION
“The third part discusses this phenomenon in LLMs in Section 13.”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“Recently, the rapid development of NLG has captured the imagination of many thanks to the advances in deep learning technologies, especially Transformer [189]-based models like BERT [29], BART [100], GPT-2 [149], and GPT-3 [16].”
BackgroundAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 1×
“This work investigates the performances of GPT-3 [13], GPT-Neo/J [141], GPT-2 [105] and a T5-based model [106].”
BackgroundAdvances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference
(2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.001.0001 · Cited by 8,890
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · cited 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
BackgroundLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816 · cited 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
Background
Research works printed but not linked: 16
- [4] Joshua Albrecht and Rebecca Hwa. 2007. A Re-examination of Machine Learning Approaches for Sentence-Level MT Evaluation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics . Association for Computational Linguistics, Prague, Czech Republic, 880-887. https://aclanthology.org/P07-1111 -
- [16] Andrzej Białecki, Robert Muir, Grant Ingersoll, and Lucid Imagination. 2012. Apache lucene 4. In SIGIR 2012 workshop on open source information retrieval . 17. -
- [53] Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. Improving Factuality and Reasoning in Language Models through Multiagent Debate. In Forty-first International Conference on Machine Learning . -
- [121] Philipp Koehn and Rebecca Knowles. 2017. Six Challenges for Neural Machine Translation. In First Workshop on Neural Machine Translation . Association for Computational Linguistics, 28-39. -
- [145] Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML . -
- [149] Tian Li, Ahmad Beirami, Maziar Sanjabi, and Virginia Smith. 2020. Tilted Empirical Risk Minimization. In International Conference on Learning Representations . -
- [164] Jiasen Lu, Jianwei Yang, Dhruv Batra, and Devi Parikh. 2018. Neural Baby Talk. In CVPR . -
- [165] Yukun Ma, Khanh Linh Nguyen, Frank Z Xing, and Erik Cambria. 2020. A Survey on Empathetic Dialogue Systems. Information Fusion 64 (2020), 50-70. -
- [175] Marianna J. Martindale, Marine Carpuat, Kevin Duh, and Paul McNamee. 2019. Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation. In MTSummit . -
- [179] Kathleen McKeown. 1992. Text Generation . Cambridge University Press. -
- [209] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. OpenAI Blog 1, 8 (2019), 9. -
- [238] Hui Su, Xiaoyu Shen, Sanqiang Zhao, Zhou Xiao, Pengwei Hu, Cheng Niu, and Jie Zhou. 2020. Diversifying Dialogue Generation with Non-Conversational Text. In 58th Annual Meeting of the Association for Computational Linguistics . ACL, 7087-7097. -
- [256] Zhaopeng Tu, Yang Liu, Lifeng Shang, Xiaohua Liu, and Hang Li. 2017. Neural Machine Translation with Reconstruction. In Thirty-First AAAI Conference on Artificial Intelligence . -
- [261] Neeraj Varshney, Wenlin Yao, Hongming Zhang, Jianshu Chen, and Dong Yu. 2023. A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation. CoRR abs/2307.03987 (2023). https://doi.org/10.48550/arXiv.2307.03987 arXiv:2307.03987 - · arXiv · doi:10.48550/arxiv.2307.03987 · Paper page
- [285] Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Xiang Gao, Chris Quirk, Rik Koncel-Kedziorski, Jianfeng Gao, Hannaneh Hajishirzi, Mari Ostendorf, et al. 2021. A Controllable Model of Grounded Response Generation. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 35. 14085-14093. -
- [291] Xinnuo Xu, Ondřej Dušek, Verena Rieser, and Ioannis Konstas. 2021. AGGGEN: Ordering and Aggregating while Generating. roceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL2021) (2021). -
Cited by
Items 3,601–3,700 of 4,844
Code-Collaborative Intelligent Query Generation Technology for Complex Relational Data
Tang, C., Lu, Z., Wang, X., Wang, Z., & Li, G. (2026) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1109/gaiis69281.2026.11519204 · Cited by 2
“However, as probabilistic generative models, they still struggle with tasks requiring strict logical consistency and factual precision, often exhibiting hallucinations and unstable reasoning [1].”
Liar, Liar, LLM on Fire: Investigating Deception in Turkish Text Generation
Bölücü, N., Yücel, Z., & Çetintaş, D. (2026) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3811025
A method for function name recovery in binaries via hierarchical semantic propagation
Kong, D.-B., Geng, Y.-Y., Guo, W., Wei, C.-J., Chen, H., Jing, F., He, L., Kong, X., & Wei, Q. (2026) · Cybersecurity · doi:10.1186/s42400-026-00602-6
“…parse_http_header ) is fundamentally different from calling an anonymous function (e.g., sub_4012A0 ) in terms of comprehension cost; for large language models, this difference similarly determines whether stable and concrete semantic judgments can be formed (Jiang et al. 2025; Ji et al. 2023).”
Banik, S., Ahuja, S., Kumari, S., et al. (2026) · International Conference on Networking and Communications (ICNWC) · doi:10.1109/icnwc68145.2026.11518382
Wei, S. T., Chen, K. Z., & Wang, T.-H. (2026) · International Conference on Educational and Information Technology · doi:10.1109/iceit68991.2026.11521597
“However, challenges such as system instability, dataset bias, and cognitive misalignment remain, particularly impacting disadvantaged learners [5, 9, 13].”
Automatic Grading of Chinese as a Second Language Reading Texts Based on Multi-LLM Weighted Voting
Han, X., & Xu, J. (2026) · International Conference on Educational and Information Technology · doi:10.1109/iceit68991.2026.11521725
“Individual LLMs often exhibit stochastic instability, inherent grading biases, and discriminative hallucination–confidently assigning erroneous levels due to corpus-specific bias or lack of domain expertise [13].”
Chen, J., & Yu, G. (2026) · International Conference on Educational and Information Technology · doi:10.1109/iceit68991.2026.11521664
SCOPE-GNN: Semantic Causal OrPhicx Explanation for Graph Neural Networks using LLMs
ABIDI, O., Selmi, M., & Farah, I. R. (2026) · doi:10.1109/iccsic69301.2026.11521307
“However, they risk semantic halluci-nation—producing plausible-sounding narratives that may not accurately reflect the actual computational mechanisms of the GNN [8].”
QSAR in the AI Era: Reflections for Advancing Chemical Safety Assessment
Kovarich, S., Gissi, A., Browne, P., Gatnik, M. F., Moncho, S., Mostrąg, A., Myatt, G. J., Pavan, M., & Bassan, A. (2026) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.6c00079
Chen, D., Yang, K., & Wang, X. A. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-22798-0_2
Dual-task transformer for social norms learning in open multi-agent systems
Messaoud, M. I. D. B., Chebout, M. S., & Mourlin, F. (2026) · Multiagent and Grid Systems · doi:10.1177/15741702261454142
“As noted in, 35 hallucination primarily arises from a parametric knowledge bias where models prioritize internal memorized information over provided source inputs.”
A Hybrid LLM-Based Architecture for Reliable Standardization of Heterogeneous Grant Information
Strykowski, S., Leszczyński, C., Kumor, S., & Śliwicki, M. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-26363-6_19
Enhance Natural Language Interaction in Virtual Being System with Enormous Domain Knowledge
Zhou, J., Zheng, L., Tong, S., Zhao, Q., Huang, Y., Liu, Z., Fang, Z., Qi, Y., Zhou, J., & Zhang, K. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522603
“This situation results in the occurrence of hallucinations [21], which indicates that the LLM begins to fabricate answers.”
SigmaForge: Retrieval-Enhanced Sigma Rule Generation with DAG-Based Quality Evaluation
Diaz-Santos, A., & Socha, K. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-23335-6_4
Xing, H., Yin, Q., Ji, X., Zhao, N., Zhu, Z., Wang, X., Zhang, Y., & Zhuang, P. (2026) · doi:10.2196/preprints.101021
From Business Meetings to Requirement Artifacts: An Agentic AI Approach with MARARE
Sami, M. A., Evangelista, G., Kemell, K., Zaina, L. A. M., Waseem, M., Zhang, Z., & Abrahamsson, P. (2026) · International Workshop on Agentic Engineering · doi:10.1145/3786167.3788405
Li, F., Furutani, K. M., & Beltran, C. J. (2026) · Tomography · doi:10.3390/tomography12050066
“In large language models (LLMs), hallucinations manifest as fluent, coherent text containing false information, fabricated citations, or statements that contradict established facts—often delivered with unwarranted confidence [240,241].”
QUANTIFYING FINANCIAL AND REPUTATIONAL LIABILITY OF AI HALLUCINATIONS IN LEGAL PRACTICE
ДЕМІДОНТ, Б. (2026) · Підприємництво та інновації · doi:10.32782/2415-3583/39.33
Norell, E. M., Gutierrez, F. X. M., Smolyak, D., Mane, H., Yue, X., Srikanth, N. P., He, X., Nguyen, T. T. X., Boyd-Graber, J. L., Dipankar, P., et al. (2026) · doi:10.2196/preprints.101898
Rytilahti, J., Puhtila, P., Weerakoon, O., Kaila, E., & Mäkilä, T. (2026) · International Workshop on Agentic Engineering · doi:10.1145/3786167.3788413
Med-Convo: A LoRA-Optimized LLaMA-2 Framework for Efficient Medical Conversations
Sajid, M. O., Ramzan, A., Khan, M. U., et al. (2026) · doi:10.1109/datascimi67380.2026.11523923
SOCAI: A Proof-of-Concept for a Conversational AI-Powered Educational Social Media Platform
Abdelaziz, M. I., & Shoukry, L. (2025) · International Conference on Computer Theory and Applications (ICCTA) · doi:10.1109/iccta68914.2025.11519790
Mitigating Cognitive Burden in Water Network Management with LLM-Based Conversational Agents
Muñoz, L. A., Vieira, A. A. C., Berná-Martínez, J. V., et al. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-26836-5_15
Scheidig, F. (2026) · Studies in Continuing Education · doi:10.1080/0158037x.2026.2675578
Yan, J. (2026) · JMIR Formative Research · doi:10.2196/preprints.100769
A Multi-Agent Cognitive Isolation Framework for Defect-Driven Power Grid Document Assessment
Yang, J., Ao, Z., Ren, H., Zhu, H., Ding, L., Wang, M., Jiang, X., & Yang, Q. (2026) · Asia Conference on Power and Electrical Engineering (ACPEE) · doi:10.1109/acpee69242.2026.11524710
“Internal heuristic loops cause semantic drift, yielding generalized criteria or outright hallucinations [7], [14].”
Cross-sectional analysis of large language models in current natural language generation challenges
Maestre, M. M., Martínez-Murillo, I., Martínez, A. M., & Lloret, E. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104922 · Cited by 1
Intelligent ERP AI Agent with RAG and LLM Integration: A Systematic Literature Review
P, N. K., & Sasikala, E. (2026) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla67915.2026.11522318 · Cited by 2
“The failure modes that is most in this context — hallucination [11], [12], must knowledge, weak review are also exactly the properties that ERP finance and security teams worry about most.”
Takuatung, S. N., & Bussracumpakorn, C. (2026) · International Conference on AI Innovations and Industry (ICAIII) · doi:10.1109/icaiii69475.2026.11521612
“Hallucinations are outputs that are not supported by facts or contradict available evidence [4].”
InfluentialMitigating Aviation Maintenance Challenges: A Technical Evaluation of AI-Enabled Sustainment
Reese, C., Xu, M., & Nicholson, S. (2026) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero66936.2026.11519873
“Hallucination mitigation further reduces risk by restricting outputs to validated technical order references, preventing spurious or unauthorized guidance [10].”
Hybrid Large-Small Model Framework for Core Business Consistency Evaluation
An, Y., Zhou, S., Liu, D., Yang, Z., Wu, Z., Fei, T., & Qin, P. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9507-5_15
RTINet: A learned in-loop filter in VVC using interaction of ResNet and Transformer
Jung, C., Fu, P., Han, J., & Liu, L. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117605
Zhang, Y., Sambamoorthi, N., Wiener, R. C., Wang, H., Shen, C., Mitra, S., Findley, P. A., & Sambamoorthi, U. (2026) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph23060694
“Hallucina-tions (e.g., fabricating posts during batch processing) and opacity underscore the need for improved transparency and bias mitigation protocols, necessitating cautious application in policy-sensitive domains [47,48].”
AI hallucinations as enterprise risk: Governance, audit, and accountability perspectives
Agarwal, P., Sharma, N., Sati, M., -, S. R., & Didwania, M. (2026) · EDPACS · doi:10.1080/07366981.2026.2677215
Söilen, K. S. (2026) · Springer eBooks · doi:10.1007/978-3-032-23069-0_7
Xu, X., Tang, J., Xu, X., Huang, X., Liu, C., Sun, G., Chen, J., Hao, P., Zhang, J., & Wu, F. (2026) · Visual Informatics · doi:10.1016/j.visinf.2026.100328
Chen, H., Liu, F., Li, B., Li, Z., & Zhang, Y. (2026) · International Conference on Mechatronics Technology and Intelligent Manufacturing (ICMTIM) · doi:10.1109/icmtim69588.2026.11525613
A Stochastic Process Model for Predicting Hallucination Dynamics in Large Language Models
Sanghavi, H., & Jawale, A. (2026) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom70271.2026.11525672
“Mitigation strategies are divided into three categories: Training-time: Data filtering and domain-specific fine-tuning [13], [14].”
Jalili, J., Gavhane, Y., Walker, E., Heinke, A., Bowd, C., Belghith, A., Fazio, M. A., Girkin, C. A., Moraes, C. G. D., Liebmann, J. M., et al. (2026) · Ophthalmology Science · doi:10.1016/j.xops.2026.101254 · Cited by 4
Chuang, K.-C., Lin, H., & Lin, H.-M. (2026) · medRxiv · doi:10.64898/2026.05.23.26353939
Wójcik, E. S., Alencynowicz, M., Skublewska‐Paszkowska, M., et al. (2026) · Computer Animation and Virtual Worlds · doi:10.1002/cav.70130
“Hallucination rate [39] measures the proportion of outputs containing unsupported or contradictory information.”
A Multi-Model Approach to Mitigate Hallucinations in Large Language Models
Singh, P., Ghosh, A., Ghosh, D., Pramanik, S., Kumari, A., Das, S., & Poddar, V. (2026) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom70271.2026.11526014
“However, many of these significant productivity gains are regularly undermined by LLM hallucinations [3], [4].”
Lin, S., Li, Y., Wang, Y., et al. (2026) · doi:10.1109/icnlp69856.2026.11527640
Yu, Y., Qiang, X., Che, J., Wen, W., Lan, Q., Smith, A., & Qiang, Y. (2026) · ICON · doi:10.1109/icnlp69856.2026.11527597
“Ji et al. [3] provide a comprehensive taxonomy and survey, distinguishing intrinsic hallucinations (contradictions with provided source input) from extrinsic hallucinations (contradictions with established world knowledge).”
LLM Agents for Analog Integrated Circuit Design: A Taxonomy and a Retrieval-Augmented Prototype
Yang, S., & He, L. (2026) · doi:10.1109/icnlp69856.2026.11527686
“These findings confirm that while the RAG framework significantly accelerates routine sizing, the “ human-in-the-loop ” mechanism remains critical for filtering non-compliant outputs [4], [21].”
Chahid, A., Chahid, I., Emharraf, M., & Belkasmi, M. G. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18894-6_21
孙, 奕. (2026) · Advances in Education · doi:10.12677/ae.2026.1651024
Algorithmic Authority Bias in AI-Assisted Learning: An Integrative Cognitive Framework
Sony, S. D., & Mus, K. (2026) · International Educational Review · doi:10.58693/ier.415 · Cited by 2
Fine-Tuning Vision Language Models for Medical Visual Question Answering
Teslaru, V., Pojoga, G., & Achirei, Ș.-D. (2026) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-032-24724-7_32
Bilgiç, B., & Turan, S. (2026) · World Journal of Psychiatry · doi:10.5498/wjp.v16.i6.119773 · Cited by 2
Alsaleh, O. I. (2026) · Telecommunication Systems · doi:10.1007/s11235-026-01462-8
“…explicitly measure trustworthiness dimensions (factuality/hallucination, calibration/abstention, and robustness to adversarial manipulation such as prompt injection and backdoor behaviors) because operational data-to-action workflows require auditable and safe outputs before actuation [17, 80–88].”
Işık, A. D., & Yerliyurt, K. (2026) · BMC Oral Health · doi:10.1186/s12903-026-08705-9 · Cited by 2
“This suggests that newer, large-parameter models are increasingly capable of minimizing “hallucinations”—the phenomenon where AI systems fabricate medical facts or citations [33].”
Qi, R., Lyu, H., Li, W., Chen, S., & Guo, X. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3882
Patient-Facing Radiology Communication with LLMs: Calibration Deficit and the Metadata Paradox
Shin, C., Park, J. H., Kim, S. J., Lee, Y. H., & Lee, H. S. (2026) · Healthcare · doi:10.3390/healthcare14111490 · Cited by 2
“The safe integration of LLMs hinges on developing robust strategies that leverage their strengths while managing failure modes [10–12].”
Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia
Cabanillas-Carbonell, M. (2026) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-032-24724-7_40
Tabatabaee, S., & Khasawneh, M. T. (2026) · IISE Transactions on Healthcare Systems Engineering · doi:10.1080/24725579.2026.2674247
Xie, H., & He, M. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774905.3794656
ReGA: Zero-Overhead Graph Alignment for Structural Hallucination Detection Without Generation
Noël, V., & Seidou, E. Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774905.3794657 · Cited by 1
Synonym Knowledge Graph Enhanced Language Model for Inconsistent Hallucination Detection
Yang, J., Zheng, H., Wang, H., & Kim, H. (2026) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3819585
Fantastic AI Text Generations and Where to Trust Them: It’s Not Magic, It’s Science!
Straub, L., Schaschek, M., Tomitza, C., & Winkelmann, A. (2026) · Lecture notes in information systems and organisation · doi:10.1007/978-3-032-08486-6_6
Tong, Q., Zhou, L., Liu, X., Liu, X., Wu, N., Wang, Y., Luo, H., Bin, Y., Tian, J., Han, D., et al. (2026) · aBIOTECH · doi:10.1016/j.abiote.2026.100059
“…a grammatically correct answer to virtually any question, including those related to scientific research, the responses may originate from unreliable sources or hallucinatory outputs [16,17], which raises concerns about the potential for generating inaccurate or even harmful information [18 – 21].”
Design Science Research in an Era of Generative AI—Challenges and Theoretical Guidelines
Heiden, P. Z., Beverungen, D., Bartelheimer, C., & Breidbach, C. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-28313-9_22
Fine-grained hierarchical multi-round iterative semantic optimization attack method for RAG systems
Chen, Q., Palade, V., Yu, Z., Deng, R., Sun, J. S. J. F., & Wu, H. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109192
Temel, C. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536646
“LLMs exhibit poor calibration [11], expressing high confidence in incorrect statements.”
Zhu, J., Fan, Y., Han, G., Shi, X., Deng, F., & Chen, J. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11591-w · Cited by 1
Ngartera, L., Nadarajah, S., Rodoumta, K., & Gningue, Y. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8060151 · Cited by 2
Bit-Lian, Y. (2026) · INTERNATIONAL JOURNAL OF CARE SCHOLARS · doi:10.31436/ijcs.v9i2.450
Mitigating LLM Limitations in Learning Environments through Retrieval-Based Knowledge Integration*
Bezerra, R., Gala, A. D. C. O. S., Marcondes, F. S., Durães, D. A., & Nováis, P. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536367
“One major concern is the problem of hallucination, where models generate potentially incorrect or misleading information due to their probabilistic nature [9], [10].”
A Sustainable Approach to Personalized Practical Learning Based on Formal Models and AI
Kazymyr, V., Zabašta, A., Khyzhniak, A., Scislo, L., & Kunicina, N. (2026) · Electronics · doi:10.3390/electronics15112364 · Cited by 1
The 14th International Workshop on News Recommendation and Analytics (INRA 2026)
Treuillier, C., Iana, A., Yadav, V., Kille, B., Lommatzsch, A., & Özgöbek, Ö. (2026) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3774935.3802529
Increasing Editor Trust in News Personalization Systems with Fact-checked Large Language Models
Wessel, T. J., Trattner, C., & Starke, A. D. (2026) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3774935.3806175
Hu, Y., Xiong, Q., Qin, Z., Watanabe, B., Wang, Y., Prpa, M., & Yoon, I. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536351 · Cited by 2
“Hal-lucinated or fabricated statements remain a known failure mode in text generation [24], and ethical and social risks (e.g., bias, privacy concerns, overreliance, and misleading authority cues) warrant careful mitigation strategies [25].”
A Framework for the Systematic Optimization of Brand Recommendation Rates in Large Language Models
Aarabi, P., Qin, Y., & Garmash, A. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536471
Tsochev, G., & Gergov, I. (2026) · Future Internet · doi:10.3390/fi18060295 · Cited by 1
Valero‐Chillerón, M. J., Llagostera‐Reverter, I., Luna-Aleixós, D., & González‐Chordá, V. M. (2026) · Enfermería Clínica · doi:10.1016/j.enfcli.2026.502553
Beyzavi, H., Shiraskar, S., Albluwi, A., Albalawi, M., Rizk, D., Rizk, F., Rizk, P., Nehmetallah, G., Rizk, R., & Santosh, K. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536474
What Exactly is a Deepfake? A Systematic Literature Analysis of Concepts, Risks, and Potentials
Liu, Y., Padmanabhan, B., & Viswanathan, S. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536577 · Cited by 1
“However, hallucination typically refers to unintended factual errors or inconsistencies in AI outputs, while deepfakes involve intentional manipulation of sensory content [40].”
Carvalho, D., Krivić, S., Tang, T., & Ahmad, S. (2026) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3774935.3812704
Qiu, X., Sun, F., Lyu, Y., Sun, H., Wang, G., & Zhang, J. (2026) · Analytica Chimica Acta · doi:10.1016/j.aca.2026.345729
Sadallah, M., & Encelle, B. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800451 · Cited by 1
Bagayan, J. W. T., Mananghaya, D. R., Patulilic, C. Y. T., Garabiag, A. D., Vargas, V. J. G., & Lucero, H. R. (2026) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2026.150500084
Kalyanaraman, S., Gupta, R., Joshi, A. S., Joshi, K. S., Suryawanshi, J., & Jadhav, V. (2026) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds69358.2026.11540259
Taking RAG Systems to the Next Level: Reasoning That Doesn't Blow Up Your Context
Lahmy, M., & Yozevitch, R. (2026) · IEEE Swiss Conference on Data Science (SDS) · doi:10.1109/sds70563.2026.00014 · Cited by 1
“Finally, while we mitigate LLM-judge variance via bootstrap intervals, automated evaluation remains subject to stochasticity [27].”
Aljedaani, W., Alsulaymi, R., Alqahtani, G., & Feng, Y. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800454
Domain-Specific Legal AI Assistant with Retrieval-Augmented Generation (RAG)
Shahzad, K., Udoh, E., Pryce, P., & Haq, A. U. (2026) · International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11541312
“General-purpose LLMs frequently generate plausible-sounding but factually incorrect information—a phenomenon known as hallucination—and lack the jurisdiction-specific knowledge necessary for accurate legal research [2].”
Adeseye, A., Isoaho, J., Virtanen, S., et al. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.04.070
Data-Grounded LLM Framework for Intelligent Travel Planning
Seireg, H. R., Omar, A. M., Eraky, F. A., et al. (2026) · doi:10.1109/icaiset66439.2026.11541537
“Rather than depending exclusively on free-form generation, the approach grounds outputs in a curated collection of real-world entities [4], which is intended to mitigate hallucination [3] and improve the dependability of the resulting recommendations.”
Takahashi, N., Kohda, Y., & Gokon, H. (2026) · Journal of Creating Value · doi:10.1177/23949643261450309
Trust-Aware Runtime Verification for Autonomous LLM Agent Systems
Patel, T. (2026) · International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11541707 · Cited by 3
“Restrictions apply. tasks, where cascading failures are more prevalent, highlighting TARV’s ability to detect subtle early-stage anomalies before they escalate [6], [11].”
InfluentialApplication level multi-agent methodology for chatbots
Arslan, O. A., & Mete, M. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.04.101
OpsAgent: A Governance-Aware Agentic AI Framework for Autonomous Operational Reliability
Muppuri, S., Madugundi, C., & Singh, R. (2026) · International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11541300 · Cited by 1
“However, LLMs are prone to hallucination—generating plausible but factually incorrect outputs [10]—necessitating structural validation mechanisms for safety-critical deployments [11].”
Li, R., Han, S., & Guo, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6866876
Anomalies in AI Outputs Beyond Input Data Quality: The Significance of Reasoning
Royo, J. [. ]. A., Martín, Ó., Martínez, E., Montalvo, F. J. F., & Blanco‐Fernández, J. (2026) · Applied Sciences · doi:10.3390/app16115491
Evaluation Metrics for LLMs: Accuracy, Relevance, and Truthfulness
Korkut, G. B., Efe, Ç., & Bayrak, A. T. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537222
“Furthermore, as models are increasingly deployed in sensitive domains, the evaluation of truthfulness has shifted from simple fact-checking to identifying sophisticated patterns of misinformation and hallucinations [3].”
Assessing the Stability of LLM-Generated Explanations in Network Security via Repeated Sampling
Turner, J., Gulum, M. A., & Kantardzic, M. M. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537249
“LLM hallucination—the generation of plausible but factually incorrect or unsupported content—is a well-recognized failure mode [5].”
Chawla, R., Dahiya, S., Singh, G., & Fortino, G. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3691181 · Cited by 1
“Prior work has categorized types of hallucinations and proposed evaluation frameworks to assess their impact [51], [52], [53], reinforcing the need for robust mitigation strategies.”
Making Sense of Sensors: Improving LLM Interpretation of Time-Series Data
Rico, A., & Larson, K. (2026) · AI Sensors · doi:10.3390/aisens2020007
“As a result, responses generated by these systems are often non-actionable, generic, and, in many cases, factually incorrect [8].”
(Nie)pewność: nauka w obiegu problematycznych informacji. Zaufanie, platformy i odbiorcy
Czerniawska, D., & Lompe, M. (2026) · doi:10.67180/uw.9788398159807
Ram, S., Regev, O., Akdam, A., Harosh, V. B., Dominsky, O., Levin, I., Cohen, A., & Bar-On, S. (2026) · European Journal of Obstetrics & Gynecology and Reproductive Biology · doi:10.1016/j.ejogrb.2026.115218
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.




