Two-Stage Training with Reinforcement Learning for Vietnamese Financial Numerical Reasoning
Nhat-Truong Dinh, Thanh-Trung Ngo, Quoc-Bao Trinh, Duc-Vu Nguyen
- Anthology ID:
- 2025.vlsp-1.28
- Volume:
- Proceedings of the 11th International Workshop on Vietnamese Language and Speech Processing
- Month:
- October
- Year:
- 2025
- Address:
- Hanoi, Vietnam
- Editors:
- Luong Chi Mai, Nguyen Thi Minh Huyen, Nguyen Thi Thu Trang
- Venues:
- VLSP | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 214–222
- Language:
- URL:
- https://preview.aclanthology.org/ingest-luhme/2025.vlsp-1.28/
- DOI:
- Cite (ACL):
- Nhat-Truong Dinh, Thanh-Trung Ngo, Quoc-Bao Trinh, and Duc-Vu Nguyen. 2025. Two-Stage Training with Reinforcement Learning for Vietnamese Financial Numerical Reasoning. In Proceedings of the 11th International Workshop on Vietnamese Language and Speech Processing, pages 214–222, Hanoi, Vietnam. Association for Computational Linguistics.
- Cite (Informal):
- Two-Stage Training with Reinforcement Learning for Vietnamese Financial Numerical Reasoning (Dinh et al., VLSP 2025)
- PDF:
- https://preview.aclanthology.org/ingest-luhme/2025.vlsp-1.28.pdf