Towards Verifiable Text Generation with Evolving Memory and Self-Reflection

Hao Sun, Hengyi Cai, Bo Wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin


Abstract
Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination. A promising solution to this issue is verifiable text generation, which prompts LLMs to generate content with citations for accuracy verification. However, verifiable text generation is non-trivial due to the focus-shifting phenomenon, the intricate reasoning needed to align the claim with correct citations, and the dilemma between the precision and breadth of retrieved documents. In this paper, we present VTG, an innovative framework for Verifiable Text Generation with evolving memory and self-reflection. VTG introduces evolving long short-term memory to retain both valuable documents and recent documents. A two-tier verifier equipped with an evidence finder is proposed to rethink and reflect on the relationship between the claim and citations. Furthermore, active retrieval and diverse query generation are utilized to enhance both the precision and breadth of the retrieved documents. We conduct extensive experiments on five datasets across three knowledge-intensive tasks and the results reveal that VTG significantly outperforms baselines.
Anthology ID:
2024.emnlp-main.469
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8211–8227
Language:
URL:
https://aclanthology.org/2024.emnlp-main.469
DOI:
Bibkey:
Cite (ACL):
Hao Sun, Hengyi Cai, Bo Wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, and Dawei Yin. 2024. Towards Verifiable Text Generation with Evolving Memory and Self-Reflection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8211–8227, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Towards Verifiable Text Generation with Evolving Memory and Self-Reflection (Sun et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.469.pdf