Papers by Liangcheng Wang

Copied to clipboard

Challenge:	Large Language Models (LLMs) offer promising avenues for automated cognitive restructuring in mental health settings, but current approaches lack the adaptability to balance conflicting therapeutic dimensions, such as empathy and rationality.
Approach:	They propose a decoupled optimization framework that implements a dimension-guided Monte Carlo tree search to train expert policies specialized for distinct therapeutic attributes rather than relying on a monolithic alignment strategy.
Outcome:	The proposed framework achieves consistent improvements over baselines across multiple evaluation dimensions, including diagnostic accuracy, contextual appropriateness, task effectiveness, and overall helpfulness, while enabling controllable cognitive restructuring generation.