Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models

Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, Bo Wang


Abstract
Learning multi-task models for jointly detecting stance and verifying rumors poses challenges due to the need for training data of stance at post level and rumor veracity at claim level, which are difficult to obtain. To address this issue, we leverage large language models (LLMs) as the foundation annotators for the joint stance detection (SD) and rumor verification (RV) tasks, dubbed as JSDRV. We introduce a novel reinforcement tuning framework to enhance the joint predictive capabilities of LLM-based SD and RV components. Specifically, we devise a policy for selecting LLM-annotated data at the two levels, employing a hybrid reward mechanism to choose high-quality labels for effective LLM fine-tuning on both tasks. Results demonstrate that JSDRV improves the capabilities of LLMs in the joint tasks, not only outperforming state-of-the-art methods but also generalizing to non-LLMs accommodated as task models.
Anthology ID:
2024.findings-acl.796
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13423–13439
Language:
URL:
https://aclanthology.org/2024.findings-acl.796
DOI:
10.18653/v1/2024.findings-acl.796
Bibkey:
Cite (ACL):
Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, and Bo Wang. 2024. Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13423–13439, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models (Yang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.796.pdf