# FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning

arXiv: https://arxiv.org/abs/2505.13419 · HTML: https://mlsanity.com/paper/2505.13419/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)
- Multimodal LLMs / vision-language models / [Multimodal emotion understanding](https://mlsanity.com/mllm/multimodal-emotion-understanding/)

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition](https://mlsanity.com/paper/2205.01782/) (2022)
- [Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition](https://mlsanity.com/paper/1811.07770/) (2018)
- [Dense Connector for MLLMs](https://mlsanity.com/paper/2405.13800/) (2024)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [EmoLLM: Multimodal Emotional Understanding Meets Large Language Models](https://mlsanity.com/paper/2406.16442/) (2024)
- [EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning](https://mlsanity.com/paper/2408.11424/) (2024)
- [MVT: Mask Vision Transformer for Facial Expression Recognition in the wild](https://mlsanity.com/paper/2106.04520/) (2021)
- [MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding](https://mlsanity.com/paper/2410.11829/) (2024)
- [Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion](https://mlsanity.com/paper/2306.11593/) (2023)
- [ExpLLM: Towards Chain of Thought for Facial Expression Recognition](https://mlsanity.com/paper/2409.02828/) (2024)
- [AU-TTT: Vision Test-Time Training model for Facial Action Unit Detection](https://mlsanity.com/paper/2503.23450/) (2025)
- [Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches](https://mlsanity.com/paper/2403.11317/) (2024)

## Built on by (most cited first, 5 of 5)

- [UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries](https://mlsanity.com/paper/2507.23372/) (2025)
- [CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation](https://mlsanity.com/paper/2508.03535/) (2025)
- [Learning What to Attend First: Modality-Importance-Guided Reasoning for Reliable Multimodal Emotion Understanding](https://mlsanity.com/paper/2512.02699/) (2025)
- [SuperFace: Preference-Aligned Facial Expression Estimation Beyond Pseudo Supervision](https://mlsanity.com/paper/2605.06179/) (2026)
- [Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations](https://mlsanity.com/paper/2606.15779/) (2026)

## Abstract (arXiv)

Facial Emotion Analysis (FEA) plays a crucial role in visual affective computing, aiming to infer a person's emotional state based on facial data. Scientifically, facial expressions (FEs) result from the coordinated movement of facial muscles, which can be decomposed into specific action units (AUs) that provide detailed emotional insights. However, traditional methods often struggle with limited interpretability, constrained generalization and reasoning abilities. Recently, Multimodal Large Language Models (MLLMs) have shown exceptional performance in various visual tasks, while they still face significant challenges in FEA due to the lack of specialized datasets and their inability to capture the intricate relationships between FEs and AUs. To address these issues, we introduce a novel FEA Instruction Dataset that provides accurate and aligned FE and AU descriptions and establishes causal reasoning relationships between them, followed by constructing a new benchmark, FEABench. Moreover, we propose FEALLM, a novel MLLM architecture designed to capture more detailed facial information, enhancing its capability in FEA tasks. Our model demonstrates strong performance on FEABench and impressive generalization capability through zero-shot evaluation on various datasets, including RAF-DB, AffectNet, BP4D, and DISFA, showcasing its robustness and effectiveness in FEA tasks. The dataset and code will be available at https://github.com/953206211/FEALLM.