# EmoPrefer: Can Large Language Models Understand Human Emotion Preferences?

arXiv: https://arxiv.org/abs/2507.04278 · HTML: https://mlsanity.com/paper/2507.04278/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2025.

## Built on by (most cited first, 6 of 6)

- [MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models](https://mlsanity.com/paper/2508.09210/) (2025)
- [Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond](https://mlsanity.com/paper/2511.00389/) (2025)
- [EmoScene: A Dual-space Dataset for Controllable Affective Image Generation](https://mlsanity.com/paper/2604.00933/) (2026)
- [MOTOR-Bench: A Real-world Dataset and Multi-agent Framework for Zero-shot Human Mental State Understanding](https://mlsanity.com/paper/2605.09703/) (2026)
- [Learning to Prefer Reliably: Error-Augmented Emotion Preference Optimization with Calibrated Fusion](https://mlsanity.com/paper/2608.24730/) (2026)
- [EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning](https://mlsanity.com/paper/2610.13353/) (2026)

## Abstract (arXiv)

Descriptive Multimodal Emotion Recognition (DMER) has garnered increasing research attention. Unlike traditional discriminative paradigms that rely on predefined emotion taxonomies, DMER aims to describe human emotional state using free-form natural language, enabling finer-grained and more interpretable emotion representations. However, this free-form prediction paradigm introduces new challenges regarding its evaluation. Previous works depend on ground-truth descriptions, but emotions are inherently tied to diverse human behaviors, and generating a comprehensive and accurate description is inherently demanding. Other researchers reformulate this problem into a more tractable human preference learning task, but pairwise preference annotation involves substantial manual effort. This leads to a question: can we leverage multimodal LLMs (MLLMs) to achieve more cost-efficient preference annotation? To answer this, we propose EmoPrefer, a pioneering work exploring the potential of LLMs in decoding human emotion preferences. Specifically, we construct the first emotion preference dataset, EmoPrefer-Data, featuring high-quality preference annotations from experts. Additionally, we introduce EmoPrefer-Bench, which evaluates the performance of various MLLMs and prompting techniques in preference prediction, while also revealing new strategies to enhance their performance. To the best of our knowledge, this is the first work exploring the capabilities of LLMs in understanding human emotion preferences. Our work advances the field of DMER and lays the foundation for more intelligent human-computer interaction.