Score: 2

COMPEER: Controllable Empathetic Reinforcement Reasoning for Emotional Support Conversation

Published: August 13, 2025 | arXiv ID: 2508.09521v1

By: Yunxiao Wang , Meng Liu , Wenqi Liu and more

BigTech Affiliations: Kuaishou

Potential Business Impact:

Helps computers give better emotional support.

Emotional support conversations are crucial for promoting emotional well-being, yet current models often lack deep empathetic reasoning grounded in psychological principles. To address this, we propose controllable empathetic reasoning, which combines natural language reasoning with structured psychological steps. We construct a fine-grained dataset annotated with reasoning correctness and response preferences to enable this capability. To further enhance training, we employ reinforcement learning with a unified process-outcome reward model that delivers precise feedback. To mitigate response repetitiveness from entropy collapse, we introduce personality-based dialogue rewriting and a redundancy-aware reward reweighting strategy. Our approach significantly improves model's emotional support ability, advancing the development of empathetic, human-like support systems.

Country of Origin
🇨🇳 China

Page Count
9 pages

Category
Computer Science:
Computation and Language