Convert Language Model into a Value-based Strategic Planner
This addresses the challenge of suboptimal long-term satisfaction in emotional support conversations for individuals seeking emotional relief.
The paper tackles the problem of improving long-term satisfaction in emotional support conversations by converting language models into value-based strategic planners, achieving performance superior to multiple baselines including direct inference, self-refine, chain of thought, finetuning, and finite state machines.
Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained remarkable progress on ESC, most of these studies might not define the diagram from the state model perspective, therefore providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Q-learning on LLMs, and propose a framework called straQ*. Our framework allows a plug-and-play LLM to bootstrap the planning during ESC, determine the optimal strategy based on long-term returns, and finally guide the LLM to response. Substantial experiments on ESC datasets suggest that straQ* outperforms many baselines, including direct inference, self-refine, chain of thought, finetuning, and finite state machines.