DEEM: Dynamic Experienced Expert Modeling for Stance Detection

Xiaolong Wang, Yile Wang, Sijie Cheng, Peng Li, Yang Liu


Abstract
Recent work has made a preliminary attempt to use large language models (LLMs) to solve the stance detection task, showing promising results. However, considering that stance detection usually requires detailed background knowledge, the vanilla reasoning method may neglect the domain knowledge to make a professional and accurate analysis. Thus, there is still room for improvement of LLMs reasoning, especially in leveraging the generation capability of LLMs to simulate specific experts (i.e., multi-agents) to detect the stance. In this paper, different from existing multi-agent works that require detailed descriptions and use fixed experts, we propose a Dynamic Experienced Expert Modeling (DEEM) method which can leverage the generated experienced experts and let LLMs reason in a semi-parametric way, making the experts more generalizable and reliable. Experimental results demonstrate that DEEM consistently achieves the best results on three standard benchmarks, outperforms methods with self-consistency reasoning, and reduces the bias of LLMs.
Anthology ID:
2024.lrec-main.405
Original:
2024.lrec-main.405v1
Version 2:
2024.lrec-main.405v2
Version 3:
2024.lrec-main.405v3
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
4530–4541
Language:
URL:
https://aclanthology.org/2024.lrec-main.405
DOI:
Bibkey:
Cite (ACL):
Xiaolong Wang, Yile Wang, Sijie Cheng, Peng Li, and Yang Liu. 2024. DEEM: Dynamic Experienced Expert Modeling for Stance Detection. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4530–4541, Torino, Italia. ELRA and ICCL.
Cite (Informal):
DEEM: Dynamic Experienced Expert Modeling for Stance Detection (Wang et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.405.pdf