Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation

Do June Min, Veronica Perez-Rosas, Ken Resnicow, Rada Mihalcea


Abstract
In this paper, we study the problem of multi-reward reinforcement learning to jointly optimize for multiple text qualities for natural language generation. We focus on the task of counselor reflection generation, where we optimize the generators to simultaneously improve the fluency, coherence, and reflection quality of generated counselor responses. We introduce two novel bandit methods, DynaOpt and C-DynaOpt, which rely on the broad strategy of combining rewards into a single value and optimizing them simultaneously. Specifically, we employ non-contextual and contextual multi-arm bandits to dynamically adjust multiple reward weights during training. Through automatic and manual evaluations, we show that our proposed techniques, DynaOpt and C-DynaOpt, outperform existing naive and bandit baselines, showcasing their potential for enhancing language models.
Anthology ID:
2024.lrec-main.483
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:
5437–5449
Language:
URL:
https://aclanthology.org/2024.lrec-main.483
DOI:
Bibkey:
Cite (ACL):
Do June Min, Veronica Perez-Rosas, Ken Resnicow, and Rada Mihalcea. 2024. Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5437–5449, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation (Min et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.lrec-main.483.pdf