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 1,601–1,700 of 4,844
ChatNVD: Advancing Cybersecurity Vulnerability Assessment With Large Language Models
Chopra, S., Ahmad, H., Goel, D., & Szabo, C. (2026) · IEEE Access · doi:10.1109/access.2026.3659205 · Cited by 28
“1) Response Hallucination: One concern is response hal-lucination, wherein the LLM generates outputs that extend beyond or deviate from the provided context and established knowledge base [86].”
LLMalMorph: On the Feasibility of Generating Variant Malware Using Large-Language-Models
Akil, M. A., Li, A. S., Karim, I., Iyengar, A., Kundu, A., Parla, V., & Bertino, E. (2025) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa67132.2025.00026 · Cited by 13
“Besides, LLMs are prone to code hallucinations [28], [29], such as inventing non-existent functions or misusing APIs.”
Kusters, A., Prajod, P., Cesar, P. S., & Ali, A. E. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791288 · Cited by 9
Wikipedia and large language models: perfect pairing or perfect storm?
Thomas, P. A. (2023) · Library Hi Tech News · doi:10.1108/lhtn-03-2023-0056 · Cited by 5
Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing
Nie, L., Sun, J., Wang, Y., Du, L., Shi, H., Zhang, D., Hou, L., Li, J., & Zhai, J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26572 · Cited by 11
Azimuth: Systematic Error Analysis for Text Classification
Gauthier-melancon, G., Ayala, O. M., Brin, L., Tyler, C., Branchaud-Charron, F., Marinier, J., Grande, K., & Le, D. (2022) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2022.emnlp-demos.30 · Cited by 7
Saeed, M., Wahab, A., Ali, J., & Bonyah, E. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e21429 · Cited by 8
“From the precise identification of objects within images to the intricate comprehension of language nuances, machine learning has spearheaded breakthroughs in image recognition, deep learning, natural language generation, and language detection [1].”
BackgroundRamirez, A. M., Agarwal, K., Juraska, J., Garg, U., & Walker, M. A. (2023) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2023.sigdial-1.32 · Cited by 14
Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs
Conia, S., Li, M., Lee, D. C., Minhas, U. I., Ilyas, I. F., & Li, Y. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.100 · Cited by 14
Eyes Show the Way: Modelling Gaze Behaviour for Hallucination Detection
Maharaj, K., Saxena, A., Kumar, R., Mishra, A., & Bhattacharyya, P. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.764 · Cited by 15
„Creating God“: Religiöse Metaphorik in KI- und Technikdiskursen
Rothenhäusler, A. (2024) · De Gruyter eBooks · doi:10.1515/9783111351490-013 · Cited by 4
Tracing the Footprints of AI in Radiology Literature: A Detailed Analysis of Journal Abstracts
Meşe, İ. (2024) · RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren · doi:10.1055/a-2224-9230 · Cited by 4
“The authors of the study recommended updated editorial policies, such as AI output detectors and full disclosure practices, to uphold the integrity of academic writing [18].”
BackgroundSemantics-enabled biomedical literature analytics
Kilicoglu, H., Ensan, F., McInnes, B. T., & Wang, L. L. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104588 · Cited by 4
Towards Large Language Model Organization: A Case Study on Abstractive Summarization
Boros, K., & Oyamada, M. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386199 · Cited by 5
“While these novel approaches yield state-of-the-art results across various tasks, they exhibit significant shortcomings such as hallucinations, high computational costs, or gender bias [3] [4].”
BackgroundAnaphoric Ambiguity Resolution in Software Requirement Texts
Jafari, S. M., Yıldırım, S., Çevik, M., & Basar, A. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386192 · Cited by 4
“The low performance of text-to-text generation methods can be first attributed to a phenomenon known as hallucination , where the model generates an antecedent that either does not appear in the context or contradicts it [21].”
BackgroundCrockett, R., & Howe, R. (2024) · Advances in Educational Marketing, Administration, and Leadership · doi:10.4018/979-8-3693-0240-8.ch010 · Cited by 4
Block, J. E., Chen, Y., Budharapu, A., Anthony, L., & Dorr, B. J. (2023) · Workshop on Evaluation and Comparison of NLP Systems (Eval4NLP) · doi:10.18653/v1/2023.eval4nlp-1.7 · Cited by 8
Large Language Models in jihadist terrorism and crimes
Puczyńska, J., Podhajski, M., Wojtasik, K., & Michalak, T. (2024) · Terroryzm · doi:10.4467/27204383ter.24.012.19400 · Cited by 8
-generAItor: Tree-in-the-loop Text Generation for Language Model Explainability and Adaptation
Spinner, T., Kehlbeck, R., Sevastjanova, R., Stähle, T., Keim, D. A., Deußen, O., & El‐Assady, M. (2024) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3652028 · Cited by 15
“Even state-of-the-art language models often fail to produce output that aligns with human intentions and sticks to facts [Ji et al. 2023; LeCun 2023].”
BackgroundShlobin, N. A., & Rosseau, G. L. (2024) · World Neurosurgery · doi:10.1016/j.wneu.2024.03.149 · Cited by 6
Knowledge-augmented Methods for Natural Language Generation
Jiang, M., Lin, B. Y., Wang, S., Yi‐chong, X., Yu, W., & Zhu, C. (2024) · SpringerBriefs in computer science · doi:10.1007/978-981-97-0747-8_4 · Cited by 7
Scrutinizing the foundations: could large language models be solipsistic?
Esanu, A. (2024) · Synthese · doi:10.1007/s11229-024-04589-w · Cited by 6
“…toclassifyvariousdelusions:visual-vs text-based delusions, intrinsic (the generated output contradicts the source content) vs extrinsic (the generated output is not verifiable from the source content) delusions (Ji et al., 2023, p. 4) etc.”
InfluentialAutoRAG: Grounding text and symbols
Schulz, T., Luttermann, M., & Möller, R. (2024) · KI - Künstliche Intelligenz · doi:10.1007/s13218-024-00850-z · Cited by 4
“However, a critical chance of factually wrong but confident answers, often called hallucinations [12], remains an issue even for the latest popular LLMs [18].”
Park, K. S., & Choi, H. (2024) · Nuclear Medicine and Molecular Imaging · doi:10.1007/s13139-024-00876-z · Cited by 9
Liu, R., Zhang, Y., Yang, B., Shi, Q., & Tian, L. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103853 · Cited by 5
Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection
Hu, K., Yan, M., Chong, W.-H., Yap, Y. K., Guan, C., Zhou, J. T., & Tsang, I. W.-H. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650428 · Cited by 11
“Secondly, LLMs are prone to hallucination, generating unreliable or inaccurate content [12], [13].”
BackgroundPrimer on Generative Artificial Intelligence and Large Language Models in Medical Imaging
Kim, K., Hong, G.-S., & Kim, N. (2024) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2024.0066 · Cited by 5
PhysBERT: A text embedding model for physics scientific literature
Hellert, T., Montenegro, J., & Pollastro, A. (2024) · APL Machine Learning · doi:10.1063/5.0238090 · Cited by 13
Chen, Q., Zhou, W., Cheng, J., & Yang, J. X. (2024) · Applied Sciences · doi:10.3390/app142411529 · Cited by 9
HiBenchLLM: Historical Inquiry Benchmarking for Large Language Models
Chartier, M. A., Dakkoune, N., Bourgeois, G., & Jean, S. (2024) · Data & Knowledge Engineering · doi:10.1016/j.datak.2024.102383 · Cited by 11
Chinese Chat Room: AI Hallucinations, Epistemology and Cognition
Šekrst, K. (2024) · Studies in Logic Grammar and Rhetoric · doi:10.2478/slgr-2024-0029 · Cited by 9
Problematic Tokens: Tokenizer Bias in Large Language Models
Yang, J., Wang, Z., Lin, Y., & Zhao, Z. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825615 · Cited by 16
“The English text was translated by human beings for reference. dataset result in critical hallucinations [1], [2].”
Challenges and Opportunities of LLM-Augmented Semantic Model Creation for Dataspaces
Hoseini, S., Burgdorf, A., Paulus, A., Meisen, T., Quix, C., & Pomp, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78955-7_17 · Cited by 9
Wang, H., Guo, B., Zeng, Y., Chen, M., Ding, Y., Zhang, Y., Yao, L., & Yu, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3715098 · Cited by 12
Huo, H., Ding, X., Guo, Z., Shen, S., Ye, D., Pham, O., Milne, D., Mathieson, L., & Gardner, A. (2024) · World Engineering Education Forum - Global Engineering Deans Council (WEEF-GEDC) · doi:10.1109/weef-gedc63419.2024.10854928 · Cited by 13
Hierarchical chat-based strategies with MLLMs for Spatio-temporal action detection
Zhou, X., Wang, Y., Tao, F., Yu, H. Z., & Liu, Q. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104094 · Cited by 5
Large Language Model and Knowledge Graph Entangled Logical Reasoning
Xu, Z., Li, J., & Zhang, W. (2024) · IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg63256.2024.00061 · Cited by 7
Alotaibi, A. S., Contreras, R., Thakker, N., Mahapatro, A., Jala, S. R. A., Mohanty, E., Devulapally, P., Mirchandani, M., Marsool, M. D. M., Jain, S. M., et al. (2025) · Annals of Medicine and Surgery · doi:10.1097/ms9.0000000000003080 · Cited by 8
“It is crucial to recognize that our study offers a snapshot of the field as of 2024, and regular updates will be needed to capture future advancements in the literature.”
Yu, H.-T., Lei, C., Ge, Y., Duan, Y., Liu, X., Lynden, S. J., Kim, K., Matono, A., & Jatowt, A. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104146 · Cited by 6
Adaptation and Personalization in Human-Centered AI
Tkalčič, M., & Ferwerda, B. (2025) · Human-computer interaction series · doi:10.1007/978-3-031-61375-3_7 · Cited by 6
Graph Based Retrieval-Augmented Generation for Personalized Dietary Guidance with LLMs
Akilesh, S., Sekar, R., Tulasi Raman, R., et al. (2025) · IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS) · doi:10.1109/sceecs64059.2025.10940424 · Cited by 4
“However, a key limitation of LLMs is their tendency to hallucinate—generating outputs that may be fluent but factually incorrect [5].”
Domain-specific text embedding model for accelerator physics
Hellert, T., Montenegro, J., Venturini, M., & Pollastro, A. (2025) · Physical Review Accelerators and Beams · doi:10.1103/physrevaccelbeams.28.044601 · Cited by 19
Trustworthy Machine Learning: From Data to Models
Han, B., Yao, J., Liu, T., Li, B., Koyejo, S., & Liu, F. (2025) · Foundations and Trends® in Privacy and Security · doi:10.1561/3300000043 · Cited by 28
Bringing Two Worlds Together: The Convergence of Large Language Models and Knowledge Graphs
Cai, L., Kang, Y., Yu, C., Fu, Y., Zhang, H., & Zhao, Y. (2024) · International Conference on Automation, Robotics and Computer Engineering (ICARCE) · doi:10.1109/icarce63054.2024.00046 · Cited by 10
“The hallucination problem refers to the potential for LLM to generate responses that are inconsistent with factual information [104], and combining knowledge graphs can improve the model’s accuracy and reliability [105].”
Chen, X., Chen, Z., & Cheng, S. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00041-2 · Cited by 16
“Such methods offer computational efficiency and factual consistency due to their straightforward extraction process; however, they often yield summaries that lack coherence (Ji et al 2023; Gupta and Gupta 2019).”
Sanjani, L. A., Sarno, R., Sungkono, K. R., Haryono, A. T., Septiyanto, A. F., & Sunaryono, D. (2025) · International Conference on Computer Sciences, Engineering, and Technology Innovation (ICoCSETI) · doi:10.1109/icocseti63724.2025.11018908 · Cited by 7
“The first significant challenge is the tendency of LLM-based chatbots to produce hallucinations or inaccurate information, particularly when they encounter scenarios outside their training data [4].”
OD-Mind: An ocean drilling expert knowledge query system driven by knowledge graph
Yang, Y., Cao, W., Li, Y., Chang, R., Yang, G., Gan, C., & Wu, M. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.122135 · Cited by 7
LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Models
Tang, R., Zhu, C., Chen, B., Zhang, W., Zhu, M., Dai, X., & Guo, H. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737242 · Cited by 8
Large language modeling of hallucinatory problem mitigation based on the wheel of emotions
Wang, Z., Wang, J., Zhou, L., & You, F. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107996 · Cited by 7
Ye, Z., Qi, D., Liu, H., & Zhang, S. (2025) · Electronics · doi:10.3390/electronics14163284 · Cited by 7
Online Safety Analysis for LLMs: A Benchmark, an Assessment, and a Path Forward
Xie, X., Song, J., Zhou, Z., Huang, Y., Song, D., & Ma, L. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3603547 · Cited by 17
“Alongside the remarkable capabilities of LLMs, concerns regarding their safety issues (i.e., harmful outputs) [8], [9], [10], such as hallucination [11] and toxicity [12], have garnered increasing attention in the community.”
Human AI communication (HA-C): Transforming the role of technology in human interaction
Revolusi, P., & Febriandy, R. K. (2025) · Multidisciplinary Science Journal · doi:10.31893/multiscience.2026201 · Cited by 10
Chan, S., Li, J., Yao, B., Mahmood, A., Huang, C., Jimison, H. B., Mynatt, E. D., & Wang, D. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757442 · Cited by 27
ExClaim: Explainable Neural Claim Verification Using Rationalization
Gurrapu, S., Huang, L., & Batarseh, F. A. (2022) · IEEE Annual Software Technology Conference (STC) · doi:10.1109/stc55697.2022.00012 · Cited by 10
“Paper [50] suggests that such problems diminish user trust and fail to meet their expectations.”
BackgroundCARE: Collaborative AI-Assisted Reading Environment
Zyska, D., Dycke, N., Buchmann, J., Kuznetsov, I., & Gurevych, I. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-demo.28 · Cited by 19
Plenz, M., Opitz, J., Heinisch, P., Cimiano, P., & Frank, A. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.338 · Cited by 12
Are Experts Needed? On Human Evaluation of Counselling Reflection Generation
Wu, Z., Balloccu, S., Reiter, E., Helaoui, R., Recupero, D. R., & Riboni, D. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.382 · Cited by 22
“This is a weak point of recent generative models (Ji et al., 2022) and also a fundamental quality aspect of reflection generation, since a reflection has to first “make sense” in the context before it can be evaluated against counselling principles.”
BackgroundLiu, X., Vatn, J., Yin, S., & Maithani, V. (2023) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon51785.2023.10311736 · Cited by 10
“…after procuring the incorrect EOQ value (34.8), as option A (13) would be the closest to 34.8 instead of option B. • For GPT 3.5, the problem of artificial hallucination [20] emerged: it redefined option D as 16, making this fictional option indeed the closest to the calculation result of 15.56.”
BackgroundInfluentialAn Investigation of LLMs’ Inefficacy in Understanding Converse Relations
Qi, C., Li, B., Hui, B., Wang, B., Li, J., Wu, J., & Laili, Y. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.429 · Cited by 7
Zaman, I.-R., & Trăușan-Matu, Ș. (2024) · Information · doi:10.3390/info15030123 · Cited by 5
Ge, J., Buenaventura, A., Berrean, B., Purvis, J., Fontil, V., Lai, J. C., & Pletcher, M. J. (2024) · Hepatology Communications · doi:10.1097/hc9.0000000000000394 · Cited by 7
Leveraging Chat-Based Large Vision Language Models for Multimodal Out-of-Context Detection
Shalabi, F., Felouat, H., Nguyen, H. H., & Echizen, I. (2024) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-57916-5_8 · Cited by 12
Semantic Verification in Large Language Model-based Retrieval Augmented Generation
Martin, A., Witschel, H., Mandl, M., & Stockhecke, M. (2024) · AAAI Spring Symposia · doi:10.1609/aaaiss.v3i1.31199 · Cited by 7
Gandee, T. J., Glaze, S. C., & Giabbanelli, P. J. (2024) · Mathematics · doi:10.3390/math12131946 · Cited by 11
I See Dead People: Gray-Box Adversarial Attack on Image-to-Text Models
Lapid, R., & Sipper, M. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-74643-7_21 · Cited by 20
What is the Minimum to Trust AI?—A Requirement Analysis for (Generative) AI-Based Texts
Tomitza, C., Schaschek, M., Straub, L., & Winkelmann, A. (2025) · Lecture notes in information systems and organisation · doi:10.1007/978-3-031-80119-8_14 · Cited by 7
Studying psychosis using Natural Language Generation: A review of emerging opportunitiesPreprint
Palaniyappan, L. K., Benrimoh, D. A., Voppel, A., et al. (2023) · doi:10.31234/osf.io/rdn3k · Cited by 4
RansomCillin: Leveraging NTFS Spare Space to Recover from Ransomware AttacksPreprint
Takeuchi, K., Fujima, H., Kumamoto, T., & Yoshida, Y. (2023) · Research Square · doi:10.21203/rs.3.rs-3648063/v1 · Cited by 4
Gpt-4 Passes Most of the 297 Written Polish Board Certification ExaminationsPreprint
Pokrywka, J., Gorzelańczyk, E. J., & Kaczmarek, J. I. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4861528 · Cited by 14
Using AI to Assess the Decision-Usefulness of Corporates' Nature-related DisclosuresPreprint
Senni, C. C., Vaghefi, S. A., Schimanski, T., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4860331 · Cited by 4
Razi, A., Bouzoubaa, L. A., Pessianzadeh, A., Seberger, J. S., & Rezapour, R. (2025) · Research Square · doi:10.21203/rs.3.rs-5686084/v1 · Cited by 14
Tan, X. J., Cheor, W. L., Cheng, E. M., Lim, C. C., & Rahman, K. S. A. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.063407 · Cited by 9
“In fact, the solution generated is unreasonable with respect to the training data [67,68].”
GigaCheck: Detecting LLM-generated ContentPreprint
Tolstykh, I., Tsybina, A., Yakubson, S., Gordeev, A., Dokholyan, V., & Kuprashevich, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5381590 · Cited by 6
Bio-Eng-LLM AI Assist: A modular chatbot platform for interdisciplinary research and education
Forootani, A., Aliabadi, D. E., & Thrän, D. (2025) · SoftwareX · doi:10.1016/j.softx.2025.102260 · Cited by 10
LP-MusicCaps: LLM-Based Pseudo Music Captioning
Doh, S., Choi, K., Lee, J., & Nam, J. (2023) · arXiv · doi:10.48550/arxiv.2307.16372 · Cited by 16
“This issue, known as hallucination, can be a fun aspect when using LLMs for creative purposes [25].”
BackgroundAcademic Integrity and Students’ Ethical Use of ChatGPT in Higher Education
Shishakly, R., & Nachouki, M. (2026) · Journal of Information Technology Education: Research · doi:10.28945/5730 · Cited by 15
“One persistent issue is the reliability of AI outputs, as ChatGPT has been shown to generate factual inaccuracies, raising questions about accountability and epistemic trust (Ji et al., 2022).”
Understanding Faithfulness and Reasoning of Large Language Models on Plain Biomedical Summaries
Fang, B., Dai, X., & Karimi, S. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.578 · Cited by 4
External Data Extraction Attacks Against Retrieval-Augmented Large Language Models
He, Y., Chen, Y., Li, Y., Shao, S., Qi, L., Li, B., Tao, D., & Qin, Z. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3705326 · Cited by 4
“To mitigate these issues, retrieval-augmented generation (RAG) techniques [36], [37] have gained prominence.”
Distinguishing the Knowable from the Unknowable with Language Models
Ahdritz, G., Qin, T., Vyas, N., Barak, B., & Edelman, B. L. (2024) · arXiv · doi:10.48550/arxiv.2402.03563 · Cited by 4
Enhancing Medical Question Answering with LLMs via a Hybrid Retrieval-Augmented Generation Framework
Aljohani, B., & Alsanoosy, T. (2026) · Information · doi:10.3390/info17020133 · Cited by 3
UIGuider: Detecting Implicit Design Guidelines Using a Domain Knowledge Graph Approach
Yang, B., & Li, S. (2024) · Electronics · doi:10.3390/electronics13071210 · Cited by 3
A General Approach to Website Question Answering with Large Language Models
Ding, Y., Nie, J., Wu, D., & Liu, C. (2024) · IEEE SoutheastCon · doi:10.1109/southeastcon52093.2024.10500166 · Cited by 4
“…and fundamentally unaddressable issue of hallucinations, which involve LLMs generating factually incorrect information arising from a variety of factors including but not limited to source-reference divergence, bias and erroneous decoding [2], LLMs are unfit for the QA scenario without assistance.”
BackgroundEnhancing LLM’s Reliability by Iterative Verification Attributions with Keyword Fronting
Sui, Y., Ren, J., Tan, H., Chen, H., Li, Z., & Wang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70365-2_15 · Cited by 5
Tang, Y., Situ, J., & Huang, Y. (2024) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3675094.3678995 · Cited by 7
Kerkütlüoğlu, M., Kaya, E., & Gökmen, R. (2024) · Cureus · doi:10.7759/cureus.71472 · Cited by 7
“Within the field of AI, a hallucination refers to a response generated by an AI system that exhibits a high degree of confidence, despite lacking sufficient justification from its training data [3].”
Meta-prompting Optimized Retrieval-Augmented Generation
Rodrigues, J., & Branco, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73503-5_17 · Cited by 6
The Price of Intelligence: Three risks inherent in LLMs
Russinovich, M., Salem, A., Zanella-Béguelin, S., & Zunger, Y. (2024) · Queue · doi:10.1145/3711679 · Cited by 5
Meta-PKE: Memory-Enhanced Task-Adaptive Personal Knowledge Extraction in Daily Life
Zhong, Y., Wu, F., Guo, M., Zhang, X., Wang, M., & Wang, H. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104097 · Cited by 3
Wu, Q., Khan, M. A., Das, S., Nanda, V., Ghosh, B., Kolling, C., Speicher, T., Bindschaedler, L., Gummadi, K. P., & Terzi, E. (2025) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3701551.3703562 · Cited by 22
Li, J., Zhang, Y., Zheng, C., Liu, D., Huang, Z., & Ma, X. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713640 · Cited by 3
Towards Dialogic and On-Demand Metaphors for Interdisciplinary Reading
Yarmand, M., Reed, C. N., Tandon, U., Hekler, E. B., Weibel, N., & Wang, A. Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713698 · Cited by 4
Legal Hallucinations and the Adoption of Artificial Intelligence in the Judiciary
Herrera-Tapias, B. A., & Guzmán, D. H. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.158 · Cited by 14
TRACE: Unlocking the Potential of LLMs in Time Series Forecasting for Distributed Energy Resources
Chen, Y., & Xie, H. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3572853 · Cited by 4
“Additionally, since their outputs are determined based on probabilistic rankings rather than logical validation, it is difficult to eliminate issues such as model hallucinations and inherent biases [25].”
Toward Interactive Sound Source Localization: Better Align Sight and Sound!
Senocak, A., Ryu, H., Kim, J., Oh, T.-H., Pfister, H., & Chung, J. S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3573994 · Cited by 16
“First, most sounding objects in existing benchmarks dominate the scene, allowing the use of objectness priors to solve the problem without proper audio-visual interaction, i.e., hallucination [28].”
Music informer as an efficient model for music generation
Sun, H., Wang, X., Wang, Y., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-02792-4 · Cited by 3
Ma, Z., Mei, Y., Bruderlein, C., Gajos, K. Z., & Pan, W. (2025) · Annual Symposium on Human-Computer Interaction for Work (CHIWORK) · doi:10.1145/3729176.3729194 · Cited by 28
Tutorial Proposal: Hallucinations in Large Language Models and Large Vision-Language Models
Jing, L., Zhang, Y., & Du, X. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3734581 · Cited by 3
Bommanavar, S., & Prabhu, V. D. (2025) · Journal of Oral and Maxillofacial Pathology · doi:10.4103/jomfp.jomfp_270_24 · Cited by 3
“[2] On the other hand, ChatGPT is a radical form of chatbot that works through algorithms.”
Evaluating List Construction and Temporal Understanding capabilities of Large Language Models
Dumitru, A., Venktesh, V., Jatowt, A., & Anand, A. (2025) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3731120.3744606 · Cited by 5
MERA: Medical Electronic Records Assistant
Ibrahim, A., Khalili, A., Arabi, M., Sattar, A. H. M. S., Hosseini, A., & Serag, A. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7030073 · Cited by 7
“Issues such as model hallucinations (where LLMs generate linguistically fluent but factually inaccurate or nonsensical responses [5]), gaps in domain-specific medical knowledge, and difficulties in incorporating private or proprietary healthcare data [6] are not merely inconvenient; they can also…”
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.




