Emotional Support with LLM-based Empathetic Dialogue Generation

2025-07-17

AI Summary

Amidst surging demand for mental health support, existing empathetic dialogue generation systems exhibit suboptimal performance. To address this, we propose a large language model (LLM) optimization framework integrating prompt engineering and efficient fine-tuning. Within a unified experimental setup, we systematically compare the impact of low-rank adaptation (LoRA) versus full-parameter fine-tuning on empathetic capability, and design a structured, empathy-oriented prompt template. Our method significantly enhances the model’s depth of emotional state understanding, empathetic response accuracy, and contextual coherence. Evaluated on the authoritative NLPCC 2025 Task 8 ESC benchmark, our best-performing model ranks second, demonstrating that our approach effectively balances generation quality, training efficiency, and empathetic efficacy. This work establishes a reproducible, scalable technical paradigm for trustworthy AI-powered psychological assistance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Humans and AI: Emotional Intelligence

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Provide empathetic emotional support via dialogue
• Enhance LLMs for contextually appropriate responses
• Improve emotional understanding and response personalization

Innovation

• Leverage large-scale language models with prompt engineering
• Use Low-Rank Adaptation for parameter-efficient fine-tuning
• Combine LLMs with effective adaptation methods for ESC