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 1,001–1,100 of 4,844
ChatGPT: a reliable fertility decision-making tool?
Beilby, K. H., & Hammarberg, K. (2024) · Human Reproduction · doi:10.1093/humrep/dead272 · Cited by 18
“Additionally, ‘hallucinations’ may occur in AI-derived information with the generation of seemingly sensical text, but which has incorrect, inaccurate, or non-sensical meaning within a certain context (Ji et al. , 2023).”
BackgroundCross-Modal Retrieval for Knowledge-Based Visual Question Answering
Lerner, P., Ferret, O., & Guinaudeau, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56027-9_26 · Cited by 43
Manifestations of xenophobia in AI systems
Tomašev, N., Maynard, J. L., & Gabriel, I. (2024) · AI & Society · doi:10.1007/s00146-024-01893-4 · Cited by 25
“…al. 2023; Long 2023; Weng et al. 2023; Lu et al. 2023; Taylor 2023; Zhang et al. 2023; Besta et al. 2023), there is still a degree of skepticism on these nascent capabilities (Xu et al. 2023; Huang et al. 2023) and additional challenges that remain to be overcome (Ji et al. 2023; Shi et al. 2023).”
Fault Diagnosis and System Maintenance Based on Large Language Models and Knowledge Graphs
Li, Y., He, Y., Lian, R., & Guo, Q. (2023) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai60863.2023.10489566 · Cited by 15
“"Hallucination" refers to generating content that is meaningless or unfaithful to the sources provided [2].”
BackgroundAn Empathic GPT-Based Chatbot to Talk About Mental Disorders With Spanish Teenagers
Mármol-Romero, A. M., García-Vega, M., García-Cumbreras, M. Á., & Montejo-Ráez, A. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2344355 · Cited by 11
“Regarding major challenges and limitations, some of them are related to the undesired behaviour of LLMs, like bias [43] or hallucination [44].”
Yin, M., Wang, E., Ng, C., & Xiao, R. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642253 · Cited by 25
Report on the Search Futures Workshop at ECIR 2024
Azzopardi, L. A., Clarke, C. L. A., Kantor, P. B., Mitra, B., Trippas, J. R., Ren, Z., Aliannejadi, M., Arabzadeh, N., Chandrasekar, R., de Rijke, M., et al. (2024) · ACM SIGIR Forum · doi:10.1145/3687273.3687288 · Cited by 18
“On the other hand, text generation has the risk of hallucination [Ji et al., 2023] and aggravation of bias [Navigli et al., 2023].”
Prompt Engineering for Applied Linguistics: Elements, Examples, Techniques, and Strategies
Lin, Z. (2024) · English Language Teaching · doi:10.5539/elt.v17n9p14 · Cited by 22
“The potential causes of hallucinations might be related to the model training and overgeneralization (Ji et al., 2023).”
BackgroundLang, G., Triantoro, T., & Sharp, J. (2024) · Journal of Information Systems Education · doi:10.62273/ycij6454 · Cited by 27
“One of the key challenges affecting broader adoption of LLMs is that they sometimes generate text that is nonsensical or factually incorrect – an outcome referred to as a hallucination (Ji et al., 2023).”
BackgroundSrivastava, A., & Memon, A. M. (2024) · IEEE Access · doi:10.1109/access.2024.3446854 · Cited by 22
“However, evidence has indicated that LLMs can generate hallucinations or other content that contradicts reality [14], [15].”
BackgroundFoundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation
Kerdegari, H., Higgins, K., Veselkov, D. A., Laponogov, I., Poļaka, I., Coimbra, M. T., Pescino, J. A., Leja, M., Dinis-Ribeiro, M. J., Fleitas, T., et al. (2024) · Diagnostics · doi:10.3390/diagnostics14171912 · Cited by 16
“Firstly, FM are susceptible to “hallucination” [61], where they generate incorrect or misleading information.”
BackgroundDecompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs.
Shiri, F., Moghimifar, F., Haffari, R., Li, Y.-F., Nguyen, V., & Yoo, J. (2024) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion59988.2024.10706385 · Cited by 27
“Despite numerous remarkable breakthroughs, the hallucination problem associated with LLMs raises significant concerns, particularly in adopting these technologies in the defense context [4], [5].”
BackgroundGenerative AI Search Engines as Arbiters of Public Knowledge: An Audit of Bias and Authority
Li, A., & Sinnamon, L. (2024) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.1021 · Cited by 15
“LLMs are extremely powerful but prone to errors: generation of convincing misinformation (hallucination) (Bubeck et al., 2023; Ji et al., 2023; White, 2024), perpetuation and amplification of biases acquired through the model training process (Bender et al., 2021; White, 2024), dissemination of…”
Ghanta, S. N., Alaref, S. J., Lala, A., Nadkarni, G. N., Ganatra, S., Dani, S. S., & Mehta, J. L. (2024) · Diagnostics · doi:10.3390/diagnostics14212393 · Cited by 17
Wang, X., Ye, S., Feng, J., Feng, K., Yang, H., & Li, H. (2024) · Digital Health · doi:10.1177/20552076241297127 · Cited by 15
“25 We analyse several types of error committed by ChatGPT.”
MethodAI Chatbots: Fast Tracking Sustainability Report Analysis for Enhanced Decision Making
Boloș, M. I., Rusu, Ș., Sabău-Popa, C. D., Gherai, D. S., Negrea, A., & Crisan, M.-I. (2024) · Amfiteatru Economic · doi:10.24818/ea/2024/s18/1241 · Cited by 16
Pendyala, V. S., Kamdar, K., & Mulchandani, K. (2025) · Electronics · doi:10.3390/electronics14020256 · Cited by 22
Do multimodal large language models understand welding?
Khvatskii, G., Lee, Y. S., Angst, C., Gibbs, M., Landers, R. G., & Chawla, N. V. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103121 · Cited by 12
“While the topic continues to be widely researched [2, 3, 4], existing research on large language model (LLM) hallucinations has mostly focused on object hallucinations, particularly in text [5], leaving some emerging questions understudied.”
Conversational User Interfaces and Agents
Biancofiore, G. M., Palma, D. D., Pomo, C., Narducci, F., & Noia, T. D. (2025) · Human-computer interaction series · doi:10.1007/978-3-031-61375-3_4 · Cited by 20
Feasibility Study for Supporting Static Malware Analysis Using LLM
Fujii, S., & Yamagishi, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82362-6_1 · Cited by 31
Lewis, A., Dangol, A., Suh, H., Olszewski, A., Fogarty, J. A., & Kientz, J. A. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714131 · Cited by 22
A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
Zhao, Z., Su, Y., Li, Y., Zou, Y., Li, R., & Zhang, R. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3568147 · Cited by 25
Describe Now: User-Driven Audio Description for Blind and Low Vision Individuals
Cheema, M. S., Seifi, H., & Fazli, P. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735685 · Cited by 34
General practitioners’ opinions of generative artificial intelligence in the UK: An online survey
Kharko, A., Sanchez, C. G., Hagström, J., Gaab, J., Locher, C., McMillan, B., Sundemo, D. S., & Blease, C. (2025) · Digital Health · doi:10.1177/20552076251360863 · Cited by 22
Budnarowski, D., Jereczek, D., Detka, K., & Wieczorek, I. (2025) · Applied Sciences · doi:10.3390/app15169067 · Cited by 24
Legal AI in Low-Resource Languages: Building and Evaluating QA Systems for the Kazakh Legislation
Rakhimova, D., Turarbek, A., Karyukin, V., Sarsenbayeva, A., & Alieyev, R. (2025) · Computers · doi:10.3390/computers14090354 · Cited by 18
Villena, F., Véliz, C., García-Huidobro, R., & Aguayo, S. D. (2025) · Dentistry Review · doi:10.1016/j.dentre.2025.100160 · Cited by 31
ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER
Ghosh, S., Tyagi, U., Suri, M., Kumar, S., Ramaneswaran, S., & Manocha, D. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.8 · Cited by 17
R2D2: Robust Data-to-Text with Replacement Detection
Nan, L., Flores, L. J., Zhao, Y., Liu, Y., Benson, L., Zou, W., & Radev, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.464 · Cited by 20
MoPe: Model Perturbation based Privacy Attacks on Language Models
Li, M., Wang, J., Wang, J., & Neel, S. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.842 · Cited by 44
FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery
Yu, C., Wang, W., Liu, X., Bai, J., Song, Y., Li, Z., Gao, Y., Cao, T., & Yin, B. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.76 · Cited by 56
“As we know, language model based generation capture spurious correlation given the condition of the generation (Ji et al., 2022).”
BackgroundneuroGPT-X: Towards an Accountable Expert Opinion Tool for Vestibular SchwannomaPreprint
Guo, E., Gupta, M., Sinha, S., Rössler, K., Tatagiba, M. S., Akagami, R., Al‐Mefty, O., Sugiyama, T., Stieg, P. E., Pickett, G. E., et al. (2023) · medRxiv · doi:10.1101/2023.02.25.23286117 · Cited by 11
Homo Promptus: Predicting the impact of generative AI on human memory and creativity
Linden, K., Hachem, H.-H., & Kondyli, V. (2025) · Memory Mind & Media · doi:10.1017/mem.2025.10012 · Cited by 22
“…in content creation (Leiker et al. 2023), its reliability as a learning tool is undermined by various instabilities linked to the probabilistic nature of large language models (LLMs 2 ), algorithmic bias, and hallucinations 3 (Ji et al. 2023; Tacheva and Ramasubramanian 2023; Yan et al. 2024).”
Li, L., Kong, S., Zhao, H., Li, C., Teng, Y., & Wang, Y. (2025) · Psychiatry and Clinical Neurosciences · doi:10.1111/pcn.13781 · Cited by 10
“45 Consequently, generated responses might be out of context or simply convey false information, such as providing loose diagnosis and inaccurate advice for user ’ s complaints.”
Integrity and Misconduct, Where Does Artificial Intelligence Lead?
Nicholas, D., Herman, E., Clark, D., Abrizah, A., Revez, J. M. R., Bravo, B. R., Świgoń, M., Xu, J., & Watkinson, A. (2025) · Learned Publishing · doi:10.1002/leap.2013 · Cited by 16
“The most talked-about worry, though, concerns the so-called hallucinations—texts that give the impression of being fluent and natural, despite being unfaithful and nonsensical (Ji et al. 2023), although there are techniques that can limit their damage (Jones 2025).”
The evolution of language models: From N-Grams to LLMs, and beyond
Raeini, M. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100168 · Cited by 40
AI-Assisted Exam Variant Generation: A Human-in-the-Loop Framework for Automatic Item Creation
Burke, C. M. (2025) · Education Sciences · doi:10.3390/educsci15081029 · Cited by 16
IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
Zhu, L., Ji, D., Chen, T., Xu, P., Ye, J., & Liu, J. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00150 · Cited by 154
“This mechanism may cause models to depend excessively on superficial patterns found in the training data rather than developing a substantial understanding of fundamental logical principles [15].”
Zhou, B., & Li, K. (2025) · Geosciences · doi:10.3390/geosciences15100382 · Cited by 18
de Oliveira, R. S., & Nascimento, E. G. S. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104477 · Cited by 14
Exploring and mitigating fawning hallucinations in large language models
Shangguan, Z., Dong, Y., Wang, L., Fan, X., Leung, V. C. M., & Hu, X. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132166 · Cited by 15
Attack and defense techniques in large language models: A survey and new perspectives
Liao, Z., Chen, K., Lin, Y., Li, K., Liu, Y., Chen, H., Huang, X., & Yu, Y. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108388 · Cited by 52
Yin, Z., & Wang, S. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.115123 · Cited by 29
Yu, G., Yiu, T. W., Shen, X., & Tam, V. W. Y. (2026) · Engineering Construction & Architectural Management · doi:10.1108/ecam-10-2025-1668 · Cited by 27
Narganes-Carlón, D., Crowther, D. J., & Pearson, E. R. (2023) · Scientific Reports · doi:10.1038/s41598-023-35597-4 · Cited by 16
“In this study, we introduce a Publication-Wide Association Study (PWAS) to assess the ability of independently trained models using historical data to prioritise unstated hypotheses, which could be considered false positives or ‘hallucinations’ 17 , and are eventually validated.”
MethodGLQA: A Generation-based Method for Legal Question Answering
Zhang, W., Shen, H., Lei, T., Wang, Q., Peng, D., & Wang, X. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191483 · Cited by 12
“our model is less likely to exhibit intrinsic hallucination [12] issues such as role confusion.”
BackgroundRevisiting the Knowledge Injection Frameworks
Fu, P., Zhang, Y., Wang, H., Qiu, W., & Zhao, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.677 · Cited by 26
Bouyamourn, A. Z. A. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.192 · Cited by 32
Alarcia, R. M. G., Russo, P., Renga, A., & Golkar, A. (2024) · International Conference on Model-Based Software and Systems Engineering (MODELSWARD) · doi:10.5220/0012621900003645 · Cited by 14
“…norms and practices Despite this, shortcomings that are still faced come in the form of hallucinations (nonsensical or unfaithful text generation (Ji et al., 2023)), lack of particularly well-structured inputs and outputs, no calculation capabilities due to their statistical nature, poor domain…”
BackgroundHu, X., Li, D., Hu, B., Zheng, Z., Liu, Z., & Zhang, M. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29784 · Cited by 49
Kreutz, H., & Jahankhani, H. (2024) · Advanced sciences and technologies for security applications · doi:10.1007/978-3-031-52272-7_1 · Cited by 19
Tourists and artificial intelligence-LLM interaction: the power of forgiveness
Loureiro, S. M. C., Guerreiro, J., Friedmann, E., Lee, M. J., & Han, H. (2024) · Current Issues in Tourism · doi:10.1080/13683500.2024.2353872 · Cited by 14
“Another explanation can come from the perceived accuracy of large language models, from which information is still perceived as misleading (Ji et al., 2023; Wei et al., 2023), not transparent (Mich & Garigliano, 2023), and not updated with the latest information (knowledge embedded in its core…”
Liu, Y., Wen, Z., Weng, L., Woodman, O., Yang, Y., & Chen, W. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3410523 · Cited by 18
“However, the text generated by LLMs is not always perfect or error-free [8].”
The Design and application of RAG-based conversational agents for collaborative problem solving
Zhong, X., Xin, H., Li, W., Zhan, Z., & Cheng, M. H. M. (2024) · International Conference on Distance Education and Learning (ICDEL) · doi:10.1145/3675812.3675871 · Cited by 12
“This inevitably leads to the problem of illusion, i.e., generating content that does not follow the original text (Faithfulness) or does not conform to the facts (Factualness) [9].”
Lomas, A., & Broom, M. A. (2024) · International Journal of Obstetric Anesthesia · doi:10.1016/j.ijoa.2024.104249 · Cited by 12
Learning to Generate Structured Code Summaries From Hybrid Code Context
Zhou, Z., Li, M., Yu, H., Fan, G., Yang, P., & Huang, Z. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3439562 · Cited by 13
“On the other hand, although LLMs are intrinsically able to predict full method documentation, they suffer from hallucination [28] and their outputs have not been quantitatively evaluated yet.”
BackgroundPooryousef, V., Cordeil, M., Besançon, L., Bassed, R., & Dwyer, T. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3456212 · Cited by 16
“An additional technical limitation pertains to the use of LLMs; current LLMs generate numerous inaccuracies and hallucinations [33], potentially necessitating manual intervention, which negatively impacts efficiency and usability.”
BackgroundMahajan, A., Tran, A. H., Tseng, E. S., Como, J. J., El-Hayek, K. M., Ladha, P., & Ho, V. P. (2024) · Surgery · doi:10.1016/j.surg.2024.08.026 · Cited by 10
Feridooni, T., Javidan, A. P., Mahmood, D. N., Gomes, Z., Dueck, A. D., Wheatcroft, M., & Szalay, D. (2024) · JVS-Vascular Insights · doi:10.1016/j.jvsvi.2024.100137 · Cited by 15
Automatically learning linguistic structures for entity relation extraction
Yang, W., Chen, Y., Xu, J., Qin, Y., & Chen, P. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103904 · Cited by 15
Evaluating Synthetic Data Generation from User Generated Text
Chim, J., Ive, J., & Liakata, M. (2024) · Computational Linguistics · doi:10.1162/coli_a_00540 · Cited by 35
Kartsonis, W., Pastena, P., Hajagos, J., Hirsch, K., Gilotra, K., Murundi, S., Raiker, A., de la Bastide, C., Martinez, C., & Tassiopoulos, A. K. (2024) · Annals of Vascular Surgery · doi:10.1016/j.avsg.2024.09.059 · Cited by 13
Hartman, H., Essis, M. D., Tung, W. S., Oh, I. C., Peden, S. C., & Gianakos, A. L. (2024) · Journal of the American Academy of Orthopaedic Surgeons · doi:10.5435/jaaos-d-24-00595 · Cited by 10
A Survey on Knowledge Editing of Neural Networks
Mazzia, V., Pedrani, A., Caciolai, A., Rottmann, K., & Bernardi, D. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3498935 · Cited by 52
“This degrades the system’s performance and fails to meet user expectations in many real-world scenarios, leading to a great interest in the ability to mitigate these hallucinations.”
Domain-Specific Question-Answering Systems: A Case Study of a Carbon Neutrality Knowledge Base
Liu, L., Zhou, Y., Ma, J., Zhang, Y., & He, L. (2025) · Sustainability · doi:10.3390/su17052192 · Cited by 25
Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework
Sun, X., Li, J., Zhong, Y., Zhao, D., & Yan, R. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889448 · Cited by 42
“However, this progress introduces challenges, such as the substantial cost associated with updating model parameters and inherent deficiencies in reasoning [3]–[5].”
The use of AI large language models by university students for assignment preparation
Chen, H., van Reyk, D. M., & Oliver, B. G. G. (2025) · AJP Advances in Physiology Education · doi:10.1152/advan.00181.2024 · Cited by 11
AI-Driven Global Disaster Intelligence from News Media
Sufi, F. K., & Alsulami, M. (2025) · Mathematics · doi:10.3390/math13071083 · Cited by 14
A vision of human–AI collaboration for enhanced biological collection curation and research
Stenhouse, A., Fisher, N., Lepschi, B. J., Schmidt‐Lebuhn, A. N., Rodríguez, J., Turco, F., Reeson, A. F., Paris, C. L., & Thrall, P. H. (2025) · BioScience · doi:10.1093/biosci/biaf021 · Cited by 15
Murch, H. E., Worley, M., & Volk, F. A. (2025) · Journal of Academic Ethics · doi:10.1007/s10805-025-09634-y · Cited by 14
“…considering the possible limitations of AI with hallucinations, pla-giarized wording, bias, and unreliable sources (Alser & Waisberg, 2023; Bahammam et al., 2023; Ji et al., 2023), students who use AI should articulate steps taken to ensure rigor and quality for any AI-generated contributions.”
Large Language Models for Transforming Healthcare: A Perspective on DeepSeek‐R1
Zhou, J., Cheng, Y., He, S., Chen, Y.-C., & Chen, H. (2025) · MedComm – Future Medicine · doi:10.1002/mef2.70021 · Cited by 16
Zhou, Y., Wang, Z., Jiang, Y., Ma, B., Wang, R., Liu, Y., Zhao, Y., & Tian, Z. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3735645 · Cited by 17
MedKA: A knowledge graph-augmented approach to improve factuality in medical Large Language Models
Deng, Y., Zhao, S., Miao, Y., Zhu, J., & Li, J. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104871 · Cited by 24
Dynamic and Parametric Retrieval-Augmented Generation
Su, W., Ai, Q., Zhan, J., Dong, Q., & Liu, Y. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3731692 · Cited by 20
Large Language Model in Materials Science: Roles, Challenges, and Strategic Outlook
Zhang, J., Chen, X., Ye, X., Yang, Y., & Ai, B. (2025) · Advanced Intelligent Discovery · doi:10.1002/aidi.202500085 · Cited by 23
Ethical Issues in AI-Generated Texts: A Systematic Review and Analysis
Zhang, Y., Zhou, T., Qiao, H., & Li, T. X. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2530071 · Cited by 24
“By comparison, extrinsic hallucination is defined as the made-up output that cannot be traced to the source (Ji et al., 2023).”
InfluentialSeeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
Tang, F., Liu, C., Xu, Z., Hu, M., Huang, Z., Xue, H., Chen, Z., Peng, Z., Yang, Z., Zhou, S., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02435 · Cited by 69
“Hallucination in MLLMs [16, 17, 21, 27, 42, 46, 47, 60, 64, 91] refers to the generation of text that is misaligned with the content of the provided images.”
AI and ChatGPT Meet Surgery: A Word of Caution for Surgeon–Scientists
Rafaqat, W., Chu, D. I., & Kaafarani, H. M. A. (2023) · Annals of Surgery · doi:10.1097/sla.0000000000006000 · Cited by 11
Łajewska, W., & Balog, K. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3615132 · Cited by 14
“Natural language generation models are susceptible to hallucinations, especially if the query is insufficiently covered in the corpus, or the retrieved documents contain redundant, complementary, or contradictory information [15].”
BackgroundPatwari, M., Gutjahr, R., Marcus, R. P., Thali, Y. A., Calvarons, A. F., Raupach, R., & Maier, A. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acfc11 · Cited by 10
The use of ChatGPT in occupational medicine: opportunities and threats
Sridi, C., & Brigui, S. (2023) · Annals of Occupational and Environmental Medicine · doi:10.35371/aoem.2023.35.e42 · Cited by 13
Yu, W., & Hou, Y. (2023) · Forests · doi:10.3390/f14122412 · Cited by 13
Guest, P. C., Vasilevska, V., Al-Hamadi, A. K., Eder, J., Falkai, P., & Steiner, J. (2023) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2023.1227426 · Cited by 22
GPT in Data Science: A Practical Exploration of Model Selection
do Nascimento, N. M., Tavares, C., Alencar, P., & Cowan, D. D. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386503 · Cited by 17
“One of the critical challenges with LLMs is addressing ‘hallucinations’ [16] – instances where the models generate contextually irrelevant or factually incorrect responses.”
BackgroundLarge Language Models: AI's Legal Revolution
Bent, A. A. (2023) · Pace law review · doi:10.58948/2331-3528.2083 · Cited by 13
Trustworthiness Evaluation of Large Language Models Using Multi-Criteria Decision Making
Aksoy, M., Adem, A., & Dağdeviren, M. (2025) · IEEE Access · doi:10.1109/access.2025.3612568 · Cited by 10
“The lack of transparency in their decision-making processes makes it difficult for users to interpret or validate outputs, undermining trust [12].”
Factors Affecting Human-Generated AI Collaboration: Trust and Perceived Usefulness as Mediators
Chae, H.-S., & Yoon, C. (2025) · Information · doi:10.3390/info16100856 · Cited by 14
Chen, Q., Yin, X., Yuan, B., & Chen, Q. (2025) · Computers in Industry · doi:10.1016/j.compind.2025.104399 · Cited by 16
Can GPT Mimic Human Preferences? An Empirical and Structural InvestigationPreprint
Bauer, K., Liebich, L., & Kosfeld, M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4576036 · Cited by 9
Large Language Models for Information Retrieval: Challenges and Chances
Breuer, T., Frihat, S., Fuhr, N., Lewandowski, D., Schaer, P., & Schenkel, R. (2025) · Datenbank-Spektrum · doi:10.1007/s13222-025-00503-x · Cited by 30
Enhanced LLM-supported instructions for medication use through retrieval-augmented generation
de Jesus, D., Júnior, A. P. D. S., de Albergaria, E. T., Pagano, A. S., de Oliveira, I. J. R., Dias, C. D. S., Lage, E. M., de Oliveira, F. R., Oliveira, J. A., Gomes, I. D. C., et al. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111135 · Cited by 14
Hallucinations in medical devices
Granstedt, J., Prabhat, K. C., Deshpande, R., Garcia, V. L., & Badano, A. G. (2025) · Artificial Intelligence in the Life Sciences · doi:10.1016/j.ailsci.2025.100145 · Cited by 28
LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models
Kostikova, A., Wang, Z., Bajri, D., Pütz, O., Paaßen, B., & Eger, S. (2026) · ACM Computing Surveys · doi:10.1145/3801096 · Cited by 39
Mazhar, B., Niu, J., Ren, Y., & Haq, I. U. (2026) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2026.103072 · Cited by 16
Balanced and Explainable Social Media Analysis for Public Health with Large Language Models
Jiang, Y., Qiu, R., Zhang, Y., & Zhang, P.-F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47843-7_6 · Cited by 19
Marshall, B. H. (2023) · Patterns · doi:10.1016/j.patter.2023.100861 · Cited by 32
Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation
Yang, Z., Li, P., & Liu, Y. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.109 · Cited by 49
Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability
Sakib, M. S., & Sun, Y. (2024) · International Journal of Artificial Intelligence and Robotics Research · doi:10.1142/s2972335324500029 · Cited by 14
“One common problem with LLMs is the production of incorrect or non-existent answers, known as hallucinations 26–28 .”
BackgroundA systematic review on the dimensions of open-source disaster intelligence using GPT
Sufi, F. K. (2024) · Journal of Economy and Technology · doi:10.1016/j.ject.2024.03.004 · Cited by 14
Medical Ethics and Artificial Intelligence in Neurosurgery—How Should We Prepare?
Lee, T.-K., Park, E. H., & Lee, M. H. (2024) · World Neurosurgery · doi:10.1016/j.wneu.2024.04.067 · Cited by 14
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.




