Year: 2025
Type: conference-paper
Abstract: Large Language Models (LLMs) have shown remarkable capabilities in role-playing dialogues, yet they often struggle to maintain emotionally consistent and psychologically plausible character personalities.We present MECoT (Markov Emotional Chain-of-Thought), a framework that enhances LLMs' ability to generate authentic personality-driven dialogues through stochastic emotional transitions.Inspired by dual-process theory, MECoT combines a Markov-chain-driven emotional processor for intuitive responses with an LLMbased reasoning mechanism for rational regulation, mapped onto a 12-dimensional Emotion Circumplex Model.The framework dynamically adjusts emotional transitions using personality-weighted matrices and historical context, ensuring both emotional coherence and character consistency.We introduce the Role-playing And Personality Dialogue (RAPD) dataset, featuring diverse character interactions with fine-grained emotional annotations, along with novel metrics for evaluating emotional authenticity and personality alignment.Experimental results demonstrate MECoT's effectiveness, achieving 93.3% emotional accuracy on RAPD and substantially outperforming existing approaches.Our analysis reveals optimal emotional granularity (12-16 categories) and validates our data-driven personality optimization approach.Code and data are available at https://github.com/ turnwind/llmemochain
Authors: Yangbo Wei, Zhen Huang, Fangzhou Zhao, Qi Feng, Wei W. Xing
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412888448