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 4,201–4,300 of 4,844
Modelo replicable de ingeniería de prompts para la recuperación de literatura científica con ChatGPT
Badilla, C. A. C. (2026) · Encontros Bibli Revista Eletrônica de Biblioteconomia e Ciência da Informação · doi:10.5007/1518-2924.2026.e109140
Retrieval-Augmented Generation (RAG)— From Modular to Agentic Systems
Dong, X. L., Sharma, S., Sun, K., Wang, J., Xia, Y., Yang, X. M., Yih, S., & Zhang, F. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3816460
Aydemir, H., Esen, İ., & HASGÜL, E. (2026) · Göç Araştırmaları Dergisi · doi:10.70972/gad.1887796
Iklassov, Z., Madmoun, H., Duhot, J.-J., & Lahlou, S. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3816459
Shahri, N. S. H., & Nasharuddin, N. A. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-4302-0_18
Khan, M. A., Maazuddin, M., Abdullah, A. A., Sultan, I., Alzaeem, H. A., Qintar, M., Sharma, K. K., & Pal, B. (2026) · International Journal of Clinical Pharmacy · doi:10.1007/s11096-026-02203-2
Training a Generalist Hallucination Detector across Multiple Domains via Adaptive Layer Aggregation
Li, X., Fang, Z., Luo, Y., Deng, Y., Du, X., Ye, S., & Chen, L. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817792
Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)
Fang, C., Mola, J., Harman, M., Nawrocki, J., Shrivastava, V., Cheng, Y., Shah, J. M., Zand, K., Tripathi, M., Pudota, A., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818468
Llm and nlp-based drone control: A distributed edge computing architecture for Vietnamese
Nguyen, D.-T., Tran, P.-L., Nguyen, C.-N., Tran, H.-P., & Tran, D.-P. (2026) · FME Transaction · doi:10.5937/fme2603402n
“A primary challenge is erroneous function calling, which stems from the inherent diversity and ambiguity of natural language [18-20].”
Kilaru, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31523-6_3
Zhou, Z., Fu, J., & Qiao, S. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2705082
Gandikota, L. R., Gudipati, V. R. S., Aluvala, S. K., PONUGOTI, S., & Konda, S. T. R. (2026) · International Conference on Artificial Intelligence, Robotics and Control (AIRC) · doi:10.1109/airc69745.2026.11631386
“Automated metrics like BLEU and ROUGE capture surface-level similarities but fail to assess semantic understanding, reasoning capabilities, or factual accuracy [9].”
From Legal Advice to Legal Automation: the Scope of AI in Providing Accessible Legal Services
Sharma, J., Dubey, A., Sharma, A., Singh, B. P., Choudhary, C., & Singh, B. P. (2026) · IEEE Global Symposium on Emerging and Communication Technologies (GSEACT) · doi:10.1109/gseact68539.2026.11619997
“…documents (statutes, regulations, case decisions, legal policies) and within the framework, legal concepts and jurisdictional/ hierarchical and citation structures are preserved and even constructed within the framework (e.g., documents are legally authoritative and/or legally binding) [13-14].”
Drivers of Generative AI Acceptance in Agriculture: An AHP Study with Synthetic Experts *
Çaldağ, M. T. (2026) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit70676.2026.11631222
“Hallucination is the risk of creating false content with generative AI [19].”
Xu, S. (2026) · World Wide Web · doi:10.1007/s11280-026-01427-6
“Crucially, our preliminary experiments and recent studies indicate that without architectural constraints, LLMs are prone to “Cognitive Overload” and Hallucination [ 13 , 14 ].”
El‐Shafai, W., Azar, A. T., & Khalifa, M. A. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133857
Huanca, C. A. C. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-35635-2_14
Do Androids Dream of Electric Sheep? A Psychoanalytic Inquiry Into Large Language Models
Selek, M. (2026) · International Journal of Applied Psychoanalytic Studies · doi:10.1002/aps.70069 · Cited by 2
Huang, Z. (2026) · Journal of Civil Engineering Education · doi:10.1061/jceecd.eieng-2449
ChatGPT and Large Language Models in Contemporary Nursing
Uchmanowicz, I., Aldossary, H. M., Lee, C. S., Figura, M., Jędrzejczyk, M., Maria, M. D., Pucciarelli, G., Molka, E., Straiton, N., & Kołtuniuk, A. (2026) · Journal of Clinical Nursing · doi:10.1111/jocn.70490 · Cited by 4
Why Large Language Models Cannot Be Certified for Safety-Critical Systems
Sayakov, A. (2026) · American Impact Review · doi:10.66308/air.e2026066
Zhao, Y., Hu, T., & Jiang, S. (2026) · Symmetry · doi:10.3390/sym18081340
Trust-by-Design of an Avatar Chatbot: Advising University Students on Their Majors
Sung, B. J., Lee, G.-S., Kim, J., & Park, D.-K. (2026) · Journal of Digital Contents Society · doi:10.9728/dcs.2026.27.7.1923
Medeiros, G. H. A., & Giustozzi, F. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-31319-5_10
Kim, S.-J. (2026) · Journal of Digital Contents Society · doi:10.9728/dcs.2026.27.7.1939
SocioTable-KZ: Ethical and Privacy-Aware Bilingual Generation from Sociological Survey Data
Ospan, A., Mansurova, M., Zhangabay, Z., & Zhappar, A. (2026) · Information · doi:10.3390/info17080765
Jiang, H., Deng, Y., & Wang, Z. (2026) · Discover Computing · doi:10.1007/s10791-026-10432-2
“While LLMs have demonstrated exceptional performance across diverse Natural Language Processing (NLP) tasks, their susceptibility to hallucinations—generating factually incorrect or nonsensical content—remains a critical impediment to their application in rigorous domains [8, 22].”
Retrieval-Augmented Question answering over scientific literature for the Electron-Ion Collider
Jat, T. J., Ghosh, T., & Suresh, K. (2026) · Journal of Instrumentation · doi:10.1088/1748-0221/21/08/c08014 · Cited by 3
“The present state-of-the art Language Models either proprietary or open-source which are trained on exorbitantly large amount of text available in the internet exhibit this problem of generating fluent, confident but factually incorrect responses popularly known as hallucination [1, 2].”
A domain-adapted retrieval-augmented framework for transparent Earth system assessment
Kart, Ö., Caesar, L., Ludescher, J., & Sakschewski, B. (2026) · Communications Earth & Environment · doi:10.1038/s43247-026-03878-1
Handoff Hallucinations: Taxonomy, Benchmark, and Mitigation for Multi-agent Pipeline Failures
Jafarova, H., & Alakbarli, F. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-31319-5_22
Palthamburaj, K., & Ramesh, M. P. (2026) · Education Sciences · doi:10.3390/educsci16081270 · Cited by 1
A Divide-and-Conquer Framework for Query-Efficient Causal Discovery with Large Language Models
Hernandez, L., Boussard, M., & Leite, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-31319-5_11
Benitez, L., Gomez, A., Franco, J., & Cardozo, R. (2025) · Pharmacophore · doi:10.51847/iwekfh04ct
How do AI feedback types affect students’ continuance usage intention in AI hallucinations?
Guo, Y., Huang, T., Lu, H., Zong, L., Huang, L., & Chen, M. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2026.2711950
RAG Enabled AI Based Healthcare Assistant for Cardiovascular Symptom Analysis and Recommendation
Bhardwaj, A., Kumar, M. S., Mundukottackal, A. T., & Mythili, R. (2026) · International Conference on Data Science and Business Systems (ICDSBS) · doi:10.1109/icdsbs69077.2026.11634682
“Thanks to this technology, such models can generate outputs that include up-to-date facts while remaining transparent and free of hallucinations [3, 4].”
Incorporating Reflection Mechanism into Multi-Modal Reasoning for MLLMs
Leng, X. (2026) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce70137.2026.11634616
“However, these methods often suffer from determining hallucinations , where the model generates plausible-sounding but visually ungrounded reasoning traces [11].”
Chen, L., Cheng, L., & Qin, J. (2026) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce70137.2026.11634374
“However, in specialized fields such as maritime intelligence, they encounter persistent bottlenecks: factual hallucinations [2] and a lack of complex multi-hop reasoning.”
CausalDX: Diagnosing Long-Tail and Cascading Cloud Incidents With LLM-Guided Causal Reasoning
Chang, Z., Wu, Y.-J., Feng, H., Li, Y., Fang, Y., Liu, L., Jin, Z., Huang, D.-Q., Yang, X., Chen, P., et al. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3722256
“This challenge manifests in two distinct forms of inaccuracies in LLM-driven actions [33], [70] (cid:2) Logical Inconsistency .”
Ribeiro, A., Garrido, R., Ramos, V., Teixeira, S., & Георгиева, П. (2026) · doi:10.1109/icarai70085.2026.11635662
“However, LLMs face two fundamental limitations: they cannot access information after their training cutoff date, and they struggle to accurately recall knowledge that appears infrequently in training corpora, often resulting in hallucinations [1], [2].”
He, Y., Zhu, J., Wang, J., Li, Y., Zhang, X., Zhang, X., Qiu, C., Huang, Q., & Yang, K. C. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3722225
“In future work, more advanced vision-language models tailored Hallucination Phenomena and Countermeasures: Generative large models inevitably encounter hallucination issues during text generation [42].”
Oh, S. H., & Park, S. H. (2026) · IEEE Access · doi:10.1109/access.2026.3722268
“This increases the users’ burden to individually verify the accuracy of information, thereby reducing overall trust in the information [5].”
Multilingual Humanoid Chatbot for Customer Support
Shushanth, C., Abhi, K., Reddy, A. S., & Velpuru, M. S. (2026) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon69332.2026.11629961
“Unfortunately, a significant limitation of standard LLMs is that when prompted to answer a question about a particular institution (like tuition costs, campus amenities, etc.), they can ”hallucinate,” meaning that they can respond with incorrect information [4].”
Multi-source Knowledge Graph RAG for LLM-Based Medical Diagnosis
Kespechara, K., & Mingkhwan, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35387-0_31
Recent trends of retrieval-augmented generation in healthcare: A systematic review
Landolsi, M. Y., Fadhli, I., Boufaied, A., & Romdhane, L. B. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115912
Wang, J., Davin, K. J., Kissau, S. P., & Dornburg, A. (2026) · Foreign Language Annals · doi:10.1111/flan.70069 · Cited by 1
Jabbar, S., Bougzime, O., Cruz, C., & Bertolim, M. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35387-0_36
Data and Knowledge Dual-Driven Text Embedding Approaches: A Survey
Chen, X., 詹佳青, Lin, J., Liu, H., Zhang, Q., Chen, J., & Chen, H. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3721883
A Computational Architecture for Learning Behavior Analytics in AI-Enhanced Educational System
Mariscal, R. L., Awid, N. H., Jale, K. A. O., & Sy, S. J. (2026) · International Conference on Educational Technology, Language and Technical Communication (ETLTC) · doi:10.3390/engproc2026143056
Galitsky, B. A. (2026) · AI · doi:10.3390/ai7080311 · Cited by 1
AI Hallucination in Media Art: Rethinking Endangered Species Representation
Lee, J., Jung, S., & Lim, S. (2026) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet65726.2026.11631804
“…systems, framing it as an error that must be detected, mitigated, or eliminated to ensure factual accuracy, reliability, and system performance [7] From this technical perspective, hallucination is primarily treated as an undesirable byproduct of generative models, motivating the development…”
Too human to trust? How warmth, competence, and anxiety shape employee avoidance of generative AI
Zhong, D., Wu, F., & Sun, S. L. (2026) · AI & Society · doi:10.1007/s00146-026-03272-7
A Multi-Domain Human Expert Evaluation of Clinical and Behavioral Knowledge in Large Language Models
Prahallad, P., Prahallad, P., & Desai, D. P. (2026) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet65726.2026.11632464
Deterministic Validation for Reliable LLM-Based Causal Knowledge Extraction
Foss, D. T. (2026) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet65726.2026.11632715
Zoha, A. E., Leroy, G., Galgiani, J., & Donovan, F. M. (2026) · IEEE International Conference on Healthcare Informatics · doi:10.1109/ichi69079.2026.00012
Asmi, F., Wong, A., Almugren, I., Chotia, V., & Bilinovics–Sipos, J. (2026) · Journal of Enterprise Information Management · doi:10.1108/jeim-10-2025-1027
A Review of Deep Learning-Based Question Generation: Challenges, Methods, and Future Directions
Yehia, M. F., Helmi, Y. M., & Bahloul, M. M. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01497-4
Cross-Lingual Bias in Educational Feedback Research: Making AI Mediation Visible
Ducasse, A. M., & Caño, E. (2026) · Business and Professional Communication Quarterly · doi:10.1177/23294906261467895 · Cited by 1
Mitigating GenAI-Powered Evidence Pollution for Out-Of-Context Misinformation Detection
Yan, Z., Qi, P., Hsu, W., & Lee, M. L. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00242 · Cited by 4
“Since LLMs are prone to hallucinate [46], [47], the generated polluted text may contain inaccuracies.”
Generative AI and Large Language Models in Smart Education for Metaverse-Based Learning
Omar, K., Fakhouri, H. N., & Hamad, F. F. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-3658-7.ch007
From e-Business to Geo-Smart Business: LLMs and GeoAnalytics for Contextual SME Decisions
Francisco, E. D. R., Sepúlveda, J.-E., & Insardi, A. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-3460-6.ch010
Eapen, K. C., Krothapalli, V., Vaid, R., Dhinagar, M. J., Raju, L. J. P., Goyal, R., & Irodi, A. (2026) · Indian journal of radiology and imaging - new series/Indian journal of radiology and imaging/Indian Journal of Radiology & Imaging · doi:10.1055/s-0046-1827461
“21,22 A smaller proportion oferrors were due to nonsensical output and irrelevant references provided.”
LLM-Guided Recovery Task Recognition for Power Distribution Network Resilience Enhancement
Zhang, Z., Bu, D., Li, K., et al. (2026) · International Conference on Electrical Engineering and Green Energy (CEEGE) · doi:10.1109/ceege70076.2026.11637944
“Second, the output is restricted to a predefined JSON schema, which avoids free-form operational recommendations [16], [17].”
Culturally Responsive AI-Mediated Feedback
Kodithuwakku, D. S. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9898-3.ch008
AEQAG: An Association-Enhanced Question Answering Generation Framework and its Application
Li, H., Yin, R., He, R., Yang, J., Wang, S., & Gao, J. (2026) · International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) · doi:10.1109/aiea70743.2026.11632308
“Hallucination studies indicate that LLMs may produce fluent but unsupported statements when generation lacks reliable external evidence [18], [19].”
Chen, S., Zhu, J., & Huang, C. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0288-1_15
From Rider Voices to Route-Level Evidence: A Traceable LLM Framework for Transit Co-PlanningPreprint
Qin, R., Mansouri, A., Zhen, D., Cui, Q., & Erfani, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7275101
Wang, Y., Wu, Y., Liang, S., Tang, Z., Wei, C.-H., Yu, H., & Qu, F. (2026) · Water Research · doi:10.1016/j.watres.2026.126709
Neuro-Symbolic Video Anomaly Detection via Attribute-Based Reasoning
Filippova, S., Korevaar, S., Dau, S. H., Pham, N. T., Cao, T., & Tennakoon, R. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630160
PAMI-GPT: knowledge-grounded LLMs for reliable pattern mining workflow generation
PALLA, M., Kiran, R. U., & Pogaku, A. C. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01237-z
“However, in algorithmic domains, generic retrieval alone is insufficient: Models may hallucinate API calls, misuse parameters, or generate syntactically plausible but semantically incorrect or non-executable code [10, 11].”
Sultanow, E., Loosley, A., Chircu, A. M., Arnold, J., Bayer, T., Bauer, E., Firdaus, Y. H., Ivanov, S., Rofalski, E., Ugur, S., et al. (2026) · Future Internet · doi:10.3390/fi18080436 · Cited by 1
“LLM-based dialogue systems are subject to hallucination, i.e., the generation of fluent but unsupported or false content; surveys document that this risk is systemic rather than incidental and is particularly consequential in high-stakes domains [39].”
Hybrid Intelligent Systems: Revisiting Ethical AI Architecture in the Modern Era
Medsker, L., & Virmani, S. (2026) · Springer eBooks · doi:10.1007/978-3-032-12201-8_14
Cho, J., & Lim, D. (2026) · Journal of Eye Movement Research · doi:10.3390/jemr19040089
“In this environment, AI chatbots are no longer mere conversational agents; for many users, they function as the most trusted single source of information, even though large language models are known to produce fluent but unfaithful or fabricated content [5].”
Application of Artificial Intelligence in Perinatal Mental Health: A Review
Islam, S. M. S., Gemmill, A. W., Hirshler, Y., Pascoe, M. C., & Milgrom, J. (2026) · AI · doi:10.3390/ai7080314 · Cited by 2
张, 哲. (2026) · Statistics and Applications · doi:10.12677/sa.2026.158190
Brain as Language: Neuro-Semantic Modeling of Glioblastoma RadiogenomicsPreprint
Miteva, M., & Nisheva-Pavlova, M. (2026) · Research Square · doi:10.21203/rs.3.rs-10688745/v1 · Cited by 1
Lee, H., & Kwon, H. (2026) · Trends in Higher Education · doi:10.3390/higheredu5030078
“The basic Japanese GPTs were developed directly by the course instructor to address the structural limitations of general‑purpose ChatGPT, namely the risk of hallucination and the mismatch between AI‑generated content and learners’ proficiency levels [34].”
Pham, V. T., Phan, M., Quynh, C. B., Phuc, T. C., Duy, N. T., Tien, M. V., & Son, N. N. (2026) · Malaysian Journal of Science and Advanced Technology · doi:10.56532/mjsat.v6i2.684
“However, these approaches still face challenges with hallucination and domain-specific accuracy that knowledge graph structures can help address [9], [10].”
Blackburn, D. G. (2026) · Journal of Herpetology · doi:10.1670/3163630
Gundidza, F., Kikuchi, M., & Ozono, T. (2026) · IEEE Access · doi:10.1109/access.2026.3723798
“The literature has increasingly shifted from viewing hal-lucination primarily as fabrication toward understanding it as a failure of grounding and verification under ambiguity [6], [7].”
Amugongo, L. M., Schaller, L., Wendt, H., van Dijk, R. M., Zanuttigh, E., Neumann, C., Freisinger, A., & Deska, J. (2026) · JMIR Medical Informatics · doi:10.2196/95417 · Cited by 1
di Padova, M., Guerriero, M. A., Ruberto, M., Moscatelli, F., Mancini, N., Monda, M., Messina, G., Polito, R., & Colecchia, F. P. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-31853-4_12
Faithful detection of hallucinations in event extraction via causal intervention
Yang, L., Rong, C., Chen, L., Wang, X., & Tao, Z. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116819
The Social Cost of AI Non-Use: Understanding Comparative Technological DisadvantagePreprint
Frimpong, V. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7275561
Biagini, G., Pezzati, F., Spinu, M. B., & Ranieri, M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-31853-4_27
Al-Nadaf, A. H. (2026) · Journal of Chemical Education · doi:10.1021/acs.jchemed.6c00013 · Cited by 1
Designing and Evaluating Human–AI Interaction Service Systems: An Industrial Case Study
Tugarin, N., & van Husen, C. (2026) · International Journal of Information Management Data Insights · doi:10.1016/j.jjimei.2026.100438 · Cited by 1
Lee, H. J. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-22190-2_32
Cole, R., Hemmer, P. A., Moores, L. K., Mears, D., Samuel, A., Croix, C. L. L., Pearce, E., & Elster, E. A. (2026) · JMIR Medical Education · doi:10.2196/preprints.109763
How to customize generative artificial intelligence? Case Finnish hospital construction
Nyqvist, R., Peltokorpi, A., Marjavaara, P., Lehtovaara, J., & Oksanen, S. (2026) · Construction Innovation · doi:10.1108/ci-10-2025-0464
Hiremath, S. R., Hiremath, B. N., Hiremath, S., Nandini, K., & Revathi, V. (2026) · International Conference on Advanced Computing and Knowledge Engineering (ICACKE) · doi:10.1109/icacke65470.2026.11651136
“…context is sometimes included in the generated response, automated checks for the consistency of information are limited, and LLMs can fail to include information from the retrieved context, rephrase the material incorrectly, or hallucinate information not present in the retrieved context [13].”
SwedTI: Evidence-Grounded Multi-source Web Threat Triage with Context-Aware Script Classification
Süren, E., Hacks, S., & Sigurðarson, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35586-7_7
Kumar, P., Deepankar, A., Kumar, S., et al. (2026) · IEEE Guwahati Subsection Conference (GCON) · doi:10.1109/gcon69192.2026.11648944
“Overall, existing literature provides a trade-off between detection accuracy and computational efficiency [1].”
InfluentialKim, H., Moon, J., & Baik, N. (2026) · Electronics · doi:10.3390/electronics15163643 · Cited by 1
Alsayed, M. I., Alsayed, M. M., Maghrabi, A., et al. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2026.106655
Adenuga, J. A. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1896839 · Cited by 4
ChatGPT in the literature: A bibliometric analysis
Arık, M. A., Yalman, A., LİVBERBER, T., Aydoğan, H., Şeker, T., & Şeker, M. (2026) · Journal of Information Science · doi:10.1177/01655515261476215
Alekberli, R. Z., & Karimov, H. (2026) · International Conference on Cybersecurity, Digital Forensics, and AI Applications (ICCSDFAI) · doi:10.1109/iccsdfai70505.2026.11647933
“Hallucination — factually incorrect, internally inconsistent, or ungrounded generation — has been taxonomised as intrinsic and extrinsic [15].”
Hurtado-Martínez, C., Botella, L., Sanfeliciano, A., Aranda‐Escolástico, E., & Saúl, L. Á. (2026) · European Journal of Investigation in Health Psychology and Education · doi:10.3390/ejihpe16080117
“This design addresses known risks of unsupported natural-language generation (Ji et al., 2023).”
Jeong, Y., & Ahn, S. (2026) · The Journal of Korean Association of Computer Education · doi:10.32431/kace.2026.29.7.002
Özergin, B. (2026) · Springer eBooks · doi:10.1007/978-3-658-51525-6_52
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.




