Emotional Support with LLM-based Empathetic Dialogue Generation

TL;DR

This paper develops an empathetic dialogue system using large language models with prompt engineering and fine-tuning, achieving high performance in emotional support conversations for mental health assistance.

Contribution

It introduces a combined approach of prompt engineering and fine-tuning strategies, including Low-Rank Adaptation, to enhance LLMs for emotional support dialogue generation.

Findings

Ranked second in NLPCC 2025 ESC evaluation

Effective use of parameter-efficient adaptation methods

Demonstrated potential of LLMs in emotional support tasks

Abstract

Emotional Support Conversation (ESC) aims to provide empathetic and effective emotional assistance through dialogue, addressing the growing demand for mental health support. This paper presents our solution for the NLPCC 2025 Task 8 ESC evaluation, where we leverage large-scale language models enhanced by prompt engineering and finetuning techniques. We explore both parameter-efficient Low-Rank Adaptation and full-parameter fine-tuning strategies to improve the model's ability to generate supportive and contextually appropriate responses. Our best model ranked second in the competition, highlighting the potential of combining LLMs with effective adaptation methods for ESC tasks. Future work will focus on further enhancing emotional understanding and response personalization to build more practical and reliable emotional support systems.