EmoLLM: Appraisal-Grounded Cognitive-Emotional Co-Reasoning in Large Language Models

TL;DR

EmoLLM introduces an appraisal-grounded framework for large language models that enhances emotional intelligence and factual reliability in dialogue through structured reasoning and reinforcement learning.

Contribution

The paper presents EmoLLM, a novel framework that integrates appraisal theory into LLMs for improved co-reasoning of IQ and EQ in dialogue settings.

Findings

Improves emotional state outcomes in dialogue

Enhances response quality while maintaining factual reliability

Uses an Appraisal Reasoning Graph for structured reasoning

Abstract

Large language models (LLMs) demonstrate strong cognitive intelligence (IQ), yet many real-world interactions also require emotional intelligence (EQ) to produce responses that are both factually reliable and emotionally appropriate. In settings such as emotional support, technical assistance, and consultation, effective dialogue depends on how situations are appraised with respect to the user's needs, goals, and coping capacity. Inspired by appraisal theory, we propose EmoLLM, an appraisal-grounded framework for IQ/EQ co-reasoning in dialogue. EmoLLM uses an explicit Appraisal Reasoning Graph (ARG) to structure intermediate reasoning over contextual facts, inferred user needs, appraisal dimensions, emotional states, and response strategies before generating a reply. We train EmoLLM in a multi-turn role-play environment with reinforcement learning, where reverse-perspective reasoning provides reward signals based on predicted user-side consequences of responses. Across diverse dialogue settings, EmoLLM improves emotional state outcomes and response quality over strong baselines while preserving strong factual reliability.