Deep Learning and Natural Language Processing Research: Technological Evolution and Frontier Exploration of Hallucination Problems
Research Article
Open Access
CC BY

Deep Learning and Natural Language Processing Research: Technological Evolution and Frontier Exploration of Hallucination Problems

Nuo Chen 1*
1 Faculty of Science, Dalhousie University, Halifax, Nova Scotia, Canada B3H 4R2
*Corresponding author: nuo09883@gmail.com
Published on 19 November 2025
Volume Cover
ACE Vol.207
ISSN (Print): 2755-273X
ISSN (Online): 2755-2721
ISBN (Print): 978-1-80590-539-4
ISBN (Online): 978-1-80590-540-0
Download Cover

Abstract

With the virtue of large language models (LLMs) being applied in a growing number of fields, from text generation to medical support and financial analysis, the issue of "hallucination" has gained more and more recognition. For the given instances, "hallucination" can be explained with respect to artificial intelligence outputs that imitate coherent and convincing statements regardless of the underlying fact. Continuity of such lapses not only can undermine credibility in LLMs, but also may catalyze problems in numerous strategies, such as law, health care, or education. This paper provides a critical analysis of the currently available methods of preventing hallucinations in LLMs by outlining the retrieval-augmented generation (RAG) technique, verification frameworks, and planning-based strategies. The paper particularly deals with the TruthX reformulation displayed at ACL 2024, which essentially means redefining the meaning of factualism via representation editing. This dialogue is rounded off by stressing the ongoing problems and future growth routes, while suggesting that multiple methods, human cooperation, and efficient representation control altogether can lay the foundation for many more faithful and traceable language models.

Keywords:

Large language model, Hallucination, Retrieval-augmented generation, Human-machine collaboration, Representation editor

View PDF
Chen,N. (2025). Deep Learning and Natural Language Processing Research: Technological Evolution and Frontier Exploration of Hallucination Problems. Applied and Computational Engineering,207,67-75.

References

[1]. Koehn, P., and Knowles, R. (2017). Six Challenges for Neural Machine Translation. In Proceedings of the NMT Workshop.

[2]. Lin, S., Hilton, J., Evans, O. (2021). TruthfulQA: Measuring How Models Mimic Human Falsehoods. ACL.

[3]. Lewis, P., Perez, E., Piktus, A., Petroni, F., et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. NeurIPS.

[4]. Wang, X., Wei, J., Schuurmans, D., Le, Q., et al. (2023). Self-Consistency Improves Chain-of-Thought Reasoning in Language Models. ICLR.

[5]. Dhuliawala, S., Alayrac, J.-B., et al. (2024). Chain-of-Verification Reduces Hallucination in Large Language Models. Findings of ACL.

[6]. Yang, L., Yu, Z. C., Zhang, T. J. et al. (2024). Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models. NeurIPS.

[7]. Wen, J. X. et al. (2025). CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning. ICLR.

[8]. Zhang, S. L., Yu, T., Feng, Y. (2024). TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space. ACL.

[9]. Izacard, G., and Grave, E. (2021). Leveraging Passage Retrieval with Generative Models for Open-Domain Question Answering (FiD). ICLR.

[10]. Glass, M., Shen, S., et al. (2022). RankRAG: Improved Retrieval-Augmented Generation with Re-ranking Mechanisms. NeurIPS.

[11]. Guu, K., Lee, K., Tung, Z., et al. (2020). REALM: Retrieval-Augmented Language Model Pre-Training. ACL.

[12]. Izacard, G., et al. (2022). Atlas: Few-shot Learning with Retrieval-Augmented Language Models. arXiv preprint.

[13]. Gao, L., et al. (2023). RARR: Retrieval-Augmented Refinement for Reducing Hallucination in Large Language Models. ACL.

[14]. Singhal, K., Tu, T., et al. (2023). Large Language Models Encode Clinical Knowledge. Nature.

[15]. Yao, S., Zhao, J., et al. (2023). ReAct: Synergizing Reasoning and Acting in Language Models. ICLR.

References

[1]. Koehn, P., and Knowles, R. (2017). Six Challenges for Neural Machine Translation. In Proceedings of the NMT Workshop.

[2]. Lin, S., Hilton, J., Evans, O. (2021). TruthfulQA: Measuring How Models Mimic Human Falsehoods. ACL.

[3]. Lewis, P., Perez, E., Piktus, A., Petroni, F., et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. NeurIPS.

[4]. Wang, X., Wei, J., Schuurmans, D., Le, Q., et al. (2023). Self-Consistency Improves Chain-of-Thought Reasoning in Language Models. ICLR.

[5]. Dhuliawala, S., Alayrac, J.-B., et al. (2024). Chain-of-Verification Reduces Hallucination in Large Language Models. Findings of ACL.

[6]. Yang, L., Yu, Z. C., Zhang, T. J. et al. (2024). Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models. NeurIPS.

[7]. Wen, J. X. et al. (2025). CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning. ICLR.

[8]. Zhang, S. L., Yu, T., Feng, Y. (2024). TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space. ACL.

[9]. Izacard, G., and Grave, E. (2021). Leveraging Passage Retrieval with Generative Models for Open-Domain Question Answering (FiD). ICLR.

[10]. Glass, M., Shen, S., et al. (2022). RankRAG: Improved Retrieval-Augmented Generation with Re-ranking Mechanisms. NeurIPS.

[11]. Guu, K., Lee, K., Tung, Z., et al. (2020). REALM: Retrieval-Augmented Language Model Pre-Training. ACL.

[12]. Izacard, G., et al. (2022). Atlas: Few-shot Learning with Retrieval-Augmented Language Models. arXiv preprint.

[13]. Gao, L., et al. (2023). RARR: Retrieval-Augmented Refinement for Reducing Hallucination in Large Language Models. ACL.

[14]. Singhal, K., Tu, T., et al. (2023). Large Language Models Encode Clinical Knowledge. Nature.

[15]. Yao, S., Zhao, J., et al. (2023). ReAct: Synergizing Reasoning and Acting in Language Models. ICLR.

Cite this article

Chen,N. (2025). Deep Learning and Natural Language Processing Research: Technological Evolution and Frontier Exploration of Hallucination Problems. Applied and Computational Engineering,207,67-75.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-SPML 2026 Symposium: The 2nd Neural Computing and Applications Workshop 2025

ISBN: 978-1-80590-539-4(Print) / 978-1-80590-540-0(Online)
Editor: Marwan Omar, Guozheng Rao
Conference website: https://www.confspml.org/tianjin.html
Conference date: 21 December 2025
Series: Applied and Computational Engineering
Volume number: Vol.207
ISSN: 2755-2721(Print) / 2755-273X(Online)

© 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).

For authors
For editors
For reviewers

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.