Download pdf
A review of methods for alleviating hallucination issues in large language models
- 1 Milton International School
* Author to whom correspondence should be addressed.
Abstract
Large language models have demonstrated impressive language processing capabilities in recent years, exhibiting unparalleled excellence in the field of natural language processing. However, the generated text sometimes contains hallucinations, which is the text that contradicts the knowledge in the real world, the context, and the user input. This problem is mainly due to the inherent limitations of the method itself in aspects such as data quality, the model training process, and the model generation process. The issue of hallucinations has always been closely monitored by the academic community. It is widely recognized that its potential consequences should not be underestimated. This paper systematically summarizes the research on the causes of hallucinations in large language models, and introduces mainstream classification methods as well as current measures to address the issue of hallucinations. To be more specific, the article divides the causes of hallucinations into two categories: 1. hallucinations come from the training process and 2. hallucinations come from the generation process. Also, 4 typical types of causes for the former and 5 typical types of causes for the latter are provided. Simultaneously, a detailed discussion of 16 methods to mitigate hallucinations that arise in the generation process is offered. Finally, this paper also discusses inherent flaws that may exist in large language models, aiming to help people gain a more comprehensive understanding and research into hallucinations and large language models. In general, the text details about the hallucinations that exist in the large language model. Meanwhile, according to the previous research, it is pointed out that it is difficult for the large language model based on autoregressive method for token prediction to avoid the hallucinations completely.
Keywords
Large Language Model, Hallucination, Cause Analysis, Solution
[1]. Wei, Jason, et al. "Emergent abilities of large language models." arXiv preprint arXiv:2206.07682 (2022).
[2]. J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei, "Scaling laws for neural language models," CoRR, vol. abs/2001.08361, 2020.
[3]. Stringhi, Elisabetta. "Hallucinating (or poorly fed) LLMs? The problem of data accuracy." i-lex 16.2 (2023): 54-63.
[4]. Lee, GaYoung, et al. “A Survey on Data Cleaning Methods for Improved Machine Learning Model Performance.” arXiv: Databases,arXiv: Databases, Sept. 2021.
[5]. Delétang, Grégoire, et al. "Language modeling is compression." arXiv preprint arXiv:2309.10668 (2023).
[6]. Rashkin, Hannah, et al. “Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features.” Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021,
[7]. Lee, Nayeon, et al. "Factuality enhanced language models for open-ended text generation." Advances in Neural Information Processing Systems 35 (2022): 34586-34599.
[8]. Wang, Chaojun, and Rico Sennrich. "On exposure bias, hallucination and domain shift in neural machine translation." arXiv preprint arXiv:2005.03642 (2020).
[9]. Li, Zichao, et al. "Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness." The 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
[10]. Sun, Kai, et al. "Head-to-tail: How knowledgeable are large language models (llm)? AKA will llms replace knowledge graphs?." arXiv preprint arXiv:2308.10168 (2023).
[11]. Rawte, Vipula, et al. "The Troubling Emergence of Hallucination in Large Language Models--An Extensive Definition, Quantification, and Prescriptive Remediations." arXiv preprint arXiv:2310.04988 (2023).
[12]. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM Computer. Survey., 55(12):248:1–248:38.
[13]. Li, Junyi, et al. "The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models." arXiv preprint arXiv:2401.03205 (2024).
[14]. Casper, Stephen, et al. "Open problems and fundamental limitations of reinforcement learning from human feedback." arXiv preprint arXiv:2307.15217 (2023).
[15]. Singhal, Prasann, et al. "A long way to go: Investigating length correlations in rlhf." arXiv preprint arXiv:2310.03716 (2023).
[16]. Varshney, Neeraj, et al. "A stitch in time saves nine: Detecting and mitigating hallucinations of llms by validating low-confidence generation." arXiv preprint arXiv:2307.03987 (2023).
[17]. Madaan, Aman, et al. SELF-REFINE: ITERATIVE REFINEMENT WITH SELF-FEEDBACK.
[18]. Mündler, Niels, et al. Self-Contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation.
[19]. Valmeekam, Karthik, Matthew Marquez, and Subbarao Kambhampati. "Can Large Language Models Really Improve by Self-critiquing Their Own Plans?." arXiv preprint arXiv:2310.08118 (2023).
[20]. Stechly, Kaya, Matthew Marquez, and Subbarao Kambhampati. "GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems." arXiv preprint arXiv:2310.12397 (2023).
[21]. Schaeffer, Rylan, Brando Miranda, and Sanmi Koyejo. "Are emergent abilities of large language models a mirage?." Advances in Neural Information Processing Systems 36 (2024).
Cite this article
Yin,Z. (2024). A review of methods for alleviating hallucination issues in large language models. Applied and Computational Engineering,76,258-266.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 2nd International Conference on Software Engineering and Machine Learning
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).