# SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression

arXiv: https://arxiv.org/abs/2604.18003 · HTML: https://mlsanity.com/paper/2604.18003/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [A Critical Review of Recurrent Neural Networks for Sequence Learning](https://mlsanity.com/paper/1506.00019/) (2015)
- [DialogueRNN: An Attentive RNN for Emotion Detection in Conversations](https://mlsanity.com/paper/1811.00405/) (2018)
- [DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation](https://mlsanity.com/paper/1908.11540/) (2019)
- [COSMIC: COmmonSense knowledge for eMotion Identification in Conversations](https://mlsanity.com/paper/2010.02795/) (2020)
- [BERT: A Review of Applications in Natural Language Processing and Understanding](https://mlsanity.com/paper/2103.11943/) (2021)
- [Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks](https://mlsanity.com/paper/1708.04299/) (2017)
- [MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation](https://mlsanity.com/paper/2107.06779/) (2021)
- [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://mlsanity.com/paper/2105.12907/) (2021)
- [DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations](https://mlsanity.com/paper/2106.01978/) (2021)
- [Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR](https://mlsanity.com/paper/2508.14029/) (2025)
- [Deep Imbalanced Learning for Multimodal Emotion Recognition in Conversations](https://mlsanity.com/paper/2312.06337/) (2023)
- [One-shot Entropy Minimization](https://mlsanity.com/paper/2505.20282/) (2025)
- [SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models](https://mlsanity.com/paper/2509.23863/) (2025)
- [BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversation](https://mlsanity.com/paper/2301.06745/) (2023)
- [Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation](https://mlsanity.com/paper/2507.15205/) (2025)

## Abstract (arXiv)

Emotion Recognition in Conversation (ERC) has become a fundamental capability for large language models (LLMs) in human-centric interaction. Beyond accurate recognition, coherent emotional expression is also crucial, yet both are limited by the scarcity and static nature of high-quality annotated data. In this work, we propose SELF-EMO, a self-evolution framework grounded in the hypothesis that better emotion prediction leads to more consistent emotional responses. We introduce two auxiliary tasks, emotional understanding and emotional expression, and design a role-based self-play paradigm where the model acts as both an emotion recognizer and a dialogue responder. Through iterative interactions, the model generates diverse conversational trajectories, enabling scalable data generation. To ensure quality, we adopt a data flywheel mechanism that filters candidate predictions and responses using a smoothed IoU-based reward and feeds selected samples back for continuous self-improvement without external supervision. We further develop SELF-GRPO, a reinforcement learning algorithm that stabilizes optimization with multi-label alignment rewards and group-level consistency signals. Experiments on IEMOCAP, MELD, and EmoryNLP show that SELF-EMO achieves state-of-the-art performance, improving accuracy by +6.33% on Qwen3-4B and +8.54% on Qwen3-8B, demonstrating strong effectiveness and generalization.