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 3,401–3,500 of 4,836
Data-Based Natural Language Generation : Evaluation and Explainability
Faille, J. (2023) · theses.fr (ABES) · doi:10.70675/3e73dd43z7aa6z4405za5cez27c78b408a3c
Development of an LLM-based Decision-making Algorithm for COLREGs-compliant Autonomous Navigation
Seo, J. H., Lim, S.-H., Jeong, S.-H., Im, S. B., Kim, S.-W., Kim, Y.-S., Kim, J.-H., & Park, J.-Y. (2026) · Journal of the Society of Naval Architects of Korea · doi:10.3744/snak.2026.63.2.69
SAGE-RAI: Design Patterns for Transparent RAG Systems
Kwarteng, J., Third, A., Mikroyannidis, A., Tarrant, D., & Domingue, J. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792929 · Cited by 1
Şahin, G. Z., & Eymirli, A. (2026) · BMC Oral Health · doi:10.1186/s12903-026-08106-y · Cited by 1
“LLMs may produce outputs that appear coherent yet lack factual accuracy, a phenomenon termed “halluci-nation” [34].”
A Modular Microservice Architecture for Retrieval-Augmented Chatbot Systems
Duta, E.-A., Aragonés, J., Jimeno-Morenilla, A. M., Mora, H., & Sánchez-Romero, J.-L. (2025) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet63943.2025.11472574 · Cited by 1
“These requirements proved a challenge when using large language models (LLMs) due to its limitations: only access to training data, high cost of retraining and “hallucinations” [4].”
Retrieval Augmentation Reduces Factual Errors in Knowledge-Intensive Language Model Tasks
Dai, T., Zhang, C., & Zou, J. (2026) · Jisuanji shenghuojia. · doi:10.54097/8jvwpk07
“Ji et al. provided an influential taxonomy of hallucination types in neural NLG, distinguishing between intrinsic hallucinations that contradict the source and extrinsic hallucinations that introduce unverifiable information, and surveyed mitigation approaches across multiple generation tasks [9].”
Quantifying Scientific Consensus in Biomedical Hypotheses via LLM-Assisted Literature ScreeningPreprint
Kim, U., Kwon, O., & Lee, D. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.06.716861
“Current LLMs, however, are rooted in probabilistic token prediction, which inherently favors statistical consensus [10].”
InfluentialPeuplement semi-automatisé de bases de connaissances à partir de documents non structurés.
Prieur, M. (2025) · theses.fr (ABES) · doi:10.70675/6c995326zb3b9z422dz9e5azbbabf8c75862
Towards efficient Knowledge Graph-based Retrieval Augmented Generation for conversational agents
Schaeffer, M. (2025) · theses.fr (ABES) · doi:10.70675/d674545fzad62z4631z9327zab503346771d · Cited by 1
Li, C., Chen, L., Tang, J., Bai, Y., Zhang, Y., Zheng, Z., Zhou, P., & Qu, Z. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792550 · Cited by 1
The Student as Prompt Engineer: Culturing Precision, Intentionality, and Metacognition
Kour, J., Kaur, S., & Bhatia, R. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8027-8.ch008
Contributions to evaluating and improving the faithfulness for text generation
Zhang, K. (2025) · theses.fr (ABES) · doi:10.70675/28453a20z78f2z4fa2za6edz700065e69e97
Enhancing RAG Pipelines with Agent-Based Hallucination Detection and Guardrails Mechanisms
Mishra, V., sharma, D. V., Seth, A., & Selvakumar, P. (2025) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet63943.2025.11471909
Research on Citizen Privacy Risk Assessment Method Based on Retrieval-Augmented GenerationPreprint
Qu, J., & Luo, F. (2026) · Research Square · doi:10.21203/rs.3.rs-9015963/v1
Iqbal, S., Ahmadi, M., Ahmadian, D., & Eskander, P. N. (2026) · Cureus · doi:10.7759/cureus.106804
“Hallucinations [20] are defined as false information generated by the LLM that is not present in the input or source data.”
Toward Human-Centered Explainability: Natural Language Explanations for Anomaly Detection
Padín-Torrente, H., Carneiro, V., & Ortega-Fernandez, I. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10717-3 · Cited by 3
NGSE: From Symbolic Control Search to Mechanism Discovery in Swarm RoboticsPreprint
Wang, C., Zhu, C., Lu, M., Bai, J., & Qiao, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6560012
Matsui, M. (2026) · Integrative Psychological and Behavioral Science · doi:10.1007/s12124-026-09997-w
“Within technical literature, hallucination is typically framed as an internal failure of the model—attributed to insufficient grounding, retrieval errors, misalignment, or poor uncertainty calibration (Maynez et al., 2020 ; Ji et al., 2023 ).”
Glanceable Verification Indicators for AI-Assisted Storytelling
Xu, M., Zhao, Z., Zeng, J., Wang, T. Y., Panetta, F., Fiebrink, R. A., Bryan–Kinns, N., & Grierson, M. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798491
Hallucination or Adaptation?: A Context-Aware Evaluation Framework for LLM Confabulation
Wang, J., & Jiang, Z. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3799103
Waiting for GPT: Probing Interaction Patterns in High-Latency RAG Chatbots
Kothbauer, T., Probst, K., & Stöckl, A. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3799266 · Cited by 1
Zhao, Z. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798387
Si, M. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3799033
Large Language Models and Stock Investing: Is the Human Factor Required?Preprint
Crisóstomo, R., & Mykhalyuk, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6446182
Query-Aware Adaptive Chunking for RAG in Mental Health and Well-Being Policy Question Answering
Kondapalli, P., Saimon, M. Z. R., Polok, S. D., Chakraborty, G. S., Abrar, M. A., & Batra, S. (2026) · International Conference on Innovative Practices in Technology and Management (ICIPTM) · doi:10.1109/iciptm69057.2026.11465692 · Cited by 1
“The survey gives a general scope to grasp generation errors within the systems of LLM [10].”
Wen, J., Chen, Y., Tang, R., Yu, X., Xu, G., Xue, L., Zhao, Q., & Weng, J. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3683285 · Cited by 1
“Restrictions apply. hallucination [33], [34]), such as proposing plausible but absent method names.”
Bridging Enterprise Silos: Multi-Agent Bot for Sales Enablement
Kusuma, D. J., Vasudevan, S. K., & Abhi, S. (2026) · International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI) · doi:10.1109/icmsci67830.2026.11469345
“…[5]; Hallucination - LLMs may generate plausible-sounding but factually incorrect information, particularly for specialized or technical topics [6]; Lack of Source Attribution - Pure LLMs cannot provide citations or trace the source of their information, making verification difficult in…”
Kuang, E., Shen, L., Soure, E. J., Fan, M., & Shinohara, K. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2638554
Optimizing Long-Form Text Generation Using LLaMA Model
Mugali, A., Mugali, B., Desai, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-19179-3_1
Beyond bias: ethnographic approaches to “AI culture”
Hau, M. F., & Hendriksen, C. (2026) · Journal of Organizational Ethnography · doi:10.1108/joe-07-2024-0035 · Cited by 2
A Novel Approach for De-Biasing and Enhanced Hallucination Mitigation in LLM
Shamseera, M. K., & Durga, R. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-17846-6_11
The Future of Self-Knowledge: A Call for Socratic AI
Dorsch, J. (2026) · Studies in brain and mind · doi:10.1007/978-3-032-16161-1_9
Baid, A., Xue, Z., & Grauman, K. L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37038-9_4 · Cited by 7
Jarsania, J., & Patel, V. (2025) · International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and Data Analytics (ICoABCD) · doi:10.1109/icoabcd67551.2025.11470747
“Ji et al. [8] provide a comprehensive taxonomy, identifying attention mechanism failures and training data biases as primary causes.”
Evaluating GraphRAG for Traceable and Interpretable Question Answering
Ahmad, A., Bracken, I. D., & Mersereau, L. (2026) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa67686.2026.11468256 · Cited by 1
Machkour, B., & Abriane, A. (2026) · ADCAIJ ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL · doi:10.14201/adcaij.33461 · Cited by 2
“Second, LLMs are known to produce hallucinations, i.e., plausible but inaccurate or fabricated statements, especially in knowledge-intensive or citation-sensitive tasks (Ji et al., 2023).”
An Emotional BDI Framework for Affective Decision Making Based on Action Tendency
황중규, Park, S.-K., & Hwang, E. (2026) · Electronics · doi:10.3390/electronics15081691 · Cited by 1
Sarchosoglou, A., Genitsarios, I., Silvis-Cividjian, N., Papavasileiou, P., Bakas, A., Papanikolaou, N., & Pappas, E. (2026) · Technical Innovations & Patient Support in Radiation Oncology · doi:10.1016/j.tipsro.2026.100404 · Cited by 2
“These patterns are consistent with broader evaluations of hallucinations in natural language generation systems [21,36].”
Patlolla, C. S. R. A. R. R. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-28493
Evaluating open-source LLMs for dental EMR generation
Wang, H., Du, W., Yang, B., Liu, M., Xu, C., Zhang, W., Xu, C., He, L., Zhang, W., Yu, Y., et al. (2026) · BMC Oral Health · doi:10.1186/s12903-026-08346-y
“Even minor errors in tooth numbering could precipitate serious consequences [32].”
James, V., Caronia, C. G., & Savargaonkar, R. (2026) · Scientific Reports · doi:10.1038/s41598-026-48326-4 · Cited by 2
“The tendency to generate incorrect or fabricated information was evident, consistent with prior reports in both medical chatbots and general LLMs 6,24 .”
Local Agentic Retrieval Augmented Generation: A Comparative Study of OpenAI and Meta LLMs
Nandwani, S., & Ostrowski, D. A. (2026) · Springer eBooks · doi:10.1007/978-3-032-18230-2_1
Văduva, A.-G., ANDREESCU, A. I., & Oprea, S. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-6136-0_36
SeerRAG: Seer-Like Routing for Uncertainty-Guided Retrieval-Augmented Generation
Li, R. U. N. Z. H. I., Yuan, S., Ji, Q., & Ge, X. (2026) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait69154.2026.11477498
“…during pre-training, leading to inherent limitations such as factual hallucinations where LLMs generate confident but factually incorrect or unsupported content due to limited or outdated parametric knowledge[3]-and knowledge obsolescence when handling specialized or real-time information[4].”
Agentic Correlation Engine: Dynamic Incident Generation Based on Knowledge Graphs
Singh, R., Ranjan, K., & Kumar, A. (2026) · Proceedings of IEEE Southeastcon · doi:10.1109/southeastcon63549.2026.11476716
“This validation phase is critical for mitigating LLM hallucinations [12].”
Jain, P. K., & Thirumalasetty, J. (2026) · IEEE SoutheastCon · doi:10.1109/southeastcon63549.2026.11476094
“…degrades as models or context windows change; retrieval-augmented generation (RAG) decay, caused by stale or fragmented vector indexes that reduce retrieval accuracy [2]; and hallucination risk, reflecting the inherent probability of non-factual or unverifiable outputs in production systems [16].”
TSKG: A Truth-Seeking Knowledge Graph Framework for Personal Knowledge Management
Grijalva, S., & Grijalva, N. (2026) · Proceedings of IEEE Southeastcon · doi:10.1109/southeastcon63549.2026.11476374
“Large language models (LLMs) integrated into PKM workflows can inadvertently amplify misinformation through confident but ungrounded responses [4], while the absence of epistemic metadata— indicating whether stored content represents verified fact, tentative hypothesis, or rhetorical…”
Liu, S., Hu, M., Xu, X., Luo, W., Geng, G., & Luo, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7078-2_36
Towards Trusted Automated Insurance: A Private Neuro-Symbolic Framework on Blockchain
Feng, Q., Tao, Y., & You, G. (2026) · doi:10.1109/iscait69154.2026.11477294
“Recent attempts to build "End-to-End" claim assessment systems using Large Multimodal Models (LMMs) have exposed a fatal flaw: stochastic hallucination[4].”
Lei, Z., Xu, Y., & Chen, S. (2026) · Applied Sciences · doi:10.3390/app16083963
Self-citationEvaluating the efficiency and factual reliability of LoRA for health misinformation detection
Li, Y., Li, X., Poo, M. C., Zhai, Y., Kamalian, L., Hon, C., & Wang, D. (2026) · Scientific Reports · doi:10.1038/s41598-026-48110-4
“To address the limitations of standard performance metrics we introduce a formal framework for hallucination analysis 1,2 .”
Knowledge Graph Multi-hop Reasoning Framework Based on LLM and Relation Path Matching
Zhao, J., Bao, J., Ma, J., & Huang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7078-2_22
Xu, Z. (2026) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait69154.2026.11477466 · Cited by 1
“First, hallucinations persist, namely outputs that are inconsistent with facts or supporting evidence [3].”
Mitigating Hallucinations in Large Language Models via Decoder Layer Skipping
Li, H., You, J., Guo, Y., Tang, K., Xie, S., & Huang, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464714
“Although recent LLMs have become more capable when incorporating many new functions, they are still struggling with hallucinations, which means that the content generated by LLMs is frequently unaligned with factual information [3].”
Kumar, A. (2026) · IEEE Access · doi:10.1109/access.2026.3683784
“Recent surveys and empirical studies consistently report that hallucinations remain a persistent failure mode across model families, especially under underspecified or adversarial prompts [28], [29].”
Merchant, P. S., & Gaba, S. (2025) · Conference on AI x Software Engineering (AIxSE) · doi:10.1109/aixse64906.2025.00019
“However, their black-box nature also introduces risks of hallucinations, where models generate confident yet factually incorrect or misleading outputs [7].”
SEARAG: Semantic Entropy-Guided Adaptive Retrieval for Multi-Hop Question Answering
Yu, D., Lin, Q.-H., Yang, Z.-L., & Zhou, L.-N. (2026) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp55912.2026.11460781
FinUA: Generating Diverse User Interactions for Financial Dialogue Systems through User Simulation
Dou, S., Sun, C., Wang, X., Liu, X., Shao, K., Chen, C., Zhang, B., & Hu, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461252
Zang, Z., Gu, W., Yang, D., Ma, S., Zhang, Z., Fan, G., Ling, W.-K., Shen, Y., & YANG, F. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464831 · Cited by 4
ERE-LLM: Entity-Relation Extraction with Large Language Model in Professional Domains
Liu, X. Y., Ding, Z., Gao, W., Li, Y., & Hu, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464200
Hierarchical Orthogonal Residual Spread for Precise Massive Editing in Large Language Models
Gu, X., Chen, G., Yang, Y., Han, J., & Zhang, A. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462295 · Cited by 4
LIFT: A Quality-Aware Data Selection Framework for Low-Resource Machine Translation
Wang, L., Yang, J., Chen, X., Li, X., & Lin, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463652
DHEval: A Dynamic Hallucination Evaluation Protocol Robust to Data Contamination
Yin, J., Li, D., Wang, W., Yang, P., Wang, H., Ma, Y., Huang, Y., & Qi, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462032
Lan, J., Li, J., Wang, B., Liu, M., Wu, D., Wang, S., Qin, B., & Hu, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462811
Li, Z., Li, X., Mao, Y., Cao, L., Huang, W., Ren, J., & Yang, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461824
CangyiYang, JiaxuZhang, BinquanJi, JiaqiWang, RuitingLi, ZheJi, & FeiliangRen (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460784
Esfandiari, N., Kiani, K., & Rastgoo, R. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02743-z
Wang, S., Pang, Z., Wang, S., & Xu, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462928
Aligning Language Models for Lyric-to-Melody Generation with Rule-Based Musical Constraints
Meng, H., Zheng, S., Zhou, S., Wang, Q., & Song, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462728
“Consequently, SFT-based models often generate melodies with musically implausible artifacts, or constraint violations [8, 3].”
Kang, D., Yuan, L., Feng, J., Grzybowski, A. E., & Jin, K. (2026) · Acta Ophthalmologica · doi:10.1111/aos.70136
DetectWild: In-The-Wild AI-Generated Text Detection Benchmark
Zhang, L., Guo, X., Zhao, Z., Cai, S., Wang, Q., Xu, W., Lin, X., & Cui, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460813 · Cited by 1
Encyclopedic web resources and generative artificial intelligence: a methodological dimension
Bykov, V. Y., & Pinchuk, O. (2026) · CTE Workshop Proceedings · doi:10.55056/cte.990 · Cited by 3
“Hallucinations directly threaten accuracy [ 8 ] , while automated text generation may compromise verifiability if source tracing is not maintained.”
Lee, J. P., Park, J.-H., Oh, D., & Kim, C. (2026) · International Journal of Sports Science & Coaching · doi:10.1177/17479541261441416 · Cited by 2
“17 After the response is generated, a post-processing pipe-line is applied.”
Kumar, R., & Raja, J. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8252-4.ch003
RAG-Enhanced LLMs for Interactive Explainability in Clinical Decision Support Systems
Mannocci, L., Naretto, F., Passaro, L., & Monreale, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-16708-8_4
Liu, H., & Xu, J. (2026) · Electronics · doi:10.3390/electronics15091802 · Cited by 1
Khandelwal, D., Tanwar, M. S., Nayer, N., & Gupta, S. C. (2026) · International Conference on Advancing Sustainable Solutions through Technologies (ICASST) · doi:10.1109/icasst68917.2026.11484152
“Ji et al. [1] provide a comprehensive taxonomy, distinguishing between intrinsic hallucinations, which contradict input context, and extrinsic hallucinations, which introduce unsupported content.”
Automating Threat-Aligned Testflows Generation Using Ontology-Grounded RAG From CTI Reports
Ahmadou, F., Nour, B., Pourzandi, M., Debbabi, M., & Assi, C. M. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3684808 · Cited by 1
“The hallucination problem produces testflows that are syntactically or semantically correct, but factually inaccurate or inconsistent [17].”
LEGEND: An LLM-Driven Soft-Constraint Adaptive Heuristic Search Framework
Zhen, T., & Yang, S. (2025) · doi:10.1145/3797552.3797702
Guettala, M., Bourekkache, S., Kazar, O., & Harous, S. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104837 · Cited by 1
Liu, Y., & Han, F. (2025) · doi:10.1145/3797552.3797561
““Paranoia” refers to the generation of nonsensi-cal or source-incompatible text, primarily manifested as logical fallacies, fabricated facts, and data-driven biases, which remain fundamentally unaddressable [ 22 ] .”
Investigating Knowledge Graphs for Context-Aware Search in Financial Transactional AI Agents
Baisenkul, N. (2026) · International Conference on Electronics, Computer and Computation · doi:10.1109/icecco67619.2026.11488774
“As noted by Ji et al. [4], the lack of multi step, temporally grounded memory systems continues to hinder the broader adoption of AI in areas requiring constant and nuanced interpretation of the latest information and datasets.”
Wu, J. (2026) · International Symposium on Big Data and Applied Statistics (ISBDAS) · doi:10.1109/isbdas69350.2026.11484104
“• Hallucination and Instability: In Zero-shot or Few-shot settings, LLMs are prone to overconfident erroneous predictions, generating emotional labels that appear plausible but are factually incorrect without a factual basis [4].”
Hootation: A GUI and API library for ontology validation and verbalization
Amith, M. “., Hao, X., Manuel, W., et al. (2026) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc67292.2026.00025
“LLMs are prone to “hallucinations” [25], potentially producing factually incorrect or logically inconsistent statements when applied to ontologies.”
Fonseca, R. D. C., Rios, R. A., Castaldoni, R., Carvalho, A. A., Lopes, T. J. S., Andrade, C. L. B., Bispo, B. V. G., Mota, L. R., & Rios, T. N. (2026) · Health Information Science and Systems · doi:10.1007/s13755-026-00458-7 · Cited by 2
“While fine-tuning on domain-specific data can improve their performance, LLMs often fail to capture the precise nuances, regulatory constraints, and expert-level accuracy required in these fields [32].”
Generative AI and Ethical Integration in Higher Education: Navigating Innovation and Responsibility
Ibrahim, U. A., Salawu, A. O., Abilbek, Z., & Aidarbayev, N. (2026) · International Conference on Electronics, Computer and Computation · doi:10.1109/icecco67619.2026.11488751
“GenAI models may fall prey to plausible but incorrect pieces of information, commonly known as "hallucinations," which are potentially hazardous when used in applications where accuracy is paramount [49].”
KEA Explain: A Neurosymbolic Framework for Explaining LLM Hallucinations
Haskins, R., & Adams, B. (2026) · Neurosymbolic Artificial Intelligence · doi:10.1177/29498732261443099 · Cited by 5
Nexarag: Democratizing Reproducible Knowledge Graph Contexts for LLM Research
Kerby, T., Fuller, B., & Moon, K. R. (2026) · The Journal of Open Source Software · doi:10.21105/joss.09910
An Intelligent Q&A System for Production Line O&M Based on Knowledge Graph and GraphRAG
Liu, Z., Chen, Z., Gao, Y., et al. (2026) · International Conference on Big Data, Information and Computer Network (BDICN) · doi:10.1145/3801228.3801238
Jiang, Z., Huang, H., & Jin, Q. (2026) · International Conference on Digital Education and Information Technology (DEIT) · doi:10.1145/3802607.3802620
GPTInflation: Oversupply of Synthetic Content and the Erosion of Attention and Trust
Alazzawi, M. S., Al-Hadrami, A., AL-Mannai, H. A., Alnoor, A., Al-Brwani, R. M., & Alhalbusi, H. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-15806-2_40
Speech recognition performance disparities between Dutch diverse speaker groups
Zhang, Y., Valck, T. D., & Scharenborg, O. (2026) · Phonetica · doi:10.1515/phon-2025-0061 · Cited by 4
“Inspection of these insertions showed that these were so-called “ hallucinations ” (Ji et al. 2023), i.e., recognized output “ that is nonsensical, or un-faithful to the provided source input ” (Ji et al. 2023: 3).”
STRATEGIES FOR CONTENT DEVELOPMENT OF WEB-ORIENTED ENCYCLOPEDIC RESOURCES IN EDUCATION
Varchenko-Trotsenko, L. O. (2026) · OPEN EDUCATIONAL E-ENVIRONMENT OF MODERN UNIVERSITY · doi:10.28925/2414-0325.2026.201
Tunçalp, D. (2026) · Journal of Management History · doi:10.1108/jmh-09-2025-0162
How foundation models will revolutionize robot swarms
Strobel, V., Dorigo, M., & Fritz, M. (2026) · Science Robotics · doi:10.1126/scirobotics.adz1543 · Cited by 1
Hussein, S. M., & Kurt, M. (2026) · Systems · doi:10.3390/systems14050474
Yuh, W. T., Ryu, S., Kim, T., & Choi, I. (2026) · Journal of Korean Neurosurgical Society · doi:10.3340/jkns.2026.0029 · Cited by 1
“This drives what is commonly called “hallucina-tion,” though the medical term confabulation is more precise— the fabrication of plausible but false information to fill knowledge gaps 44) .”
Addressing Dataset Scarcity in Music Emotion Recognition with LLMs
Aamir, J., & Donnelly, P. J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-24350-8_1
PROMPT ENGINEERING IN MARKETING AND ECONOMICS: METHODOLOGY AND METHODS
Сидорчук, Р. (2025) · Drukerovskij vestnik · doi:10.17213/2312-6469-2026-2-371-389
The Role of Prompt Engineering in Reducing Hallucination in Generative AI Models
Subbarao, M. V., Kalyani, S., Shreya, S., et al. (2026) · International Conference on Emerging Smart Computing and Informatics (ESCI) · doi:10.1109/esci68015.2026.11493253
“Prompts with thoughtful, design, including zero-shot, few-shot, role-based, or chain-of-thought forms, can aid LLMs in comprehending user intent and producing factually consistent answers [8].”
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.




