iLearn-Lab/NeurIPS25-SymMPO-13B

SymMPO: Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization

Wenqi Liu¹, Xuemeng Song², Jiaxi Li³, Yinwei Wei¹, Zheng Na⁴, Jianhua Yin¹, Liqiang Nie^5
1Shandong University    ²Southern University of Science and Technology    ³University of Georgia   
⁴National University of Singapore    ⁵Harbin Institute of Technology, Shenzhen   

---

Introduction

We present SymMPO, a framework for mitigating hallucination in multimodal large language models (MLLMs). Our method introduces a theory-consistent symmetric multimodal preference optimization approach that addresses the hallucination problem from a principled perspective. This repository provides the official implementation, pretrained checkpoints, and evaluation scripts built on top of LLaVA.

Citation

If you find our work helpful, please consider citing:

@inproceedings{
  liu2025mitigating,
  title={Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization},
  author={Wenqi Liu and Xuemeng Song and Jiaxi Li and Yinwei Wei and Na Zheng and Jianhua Yin and Liqiang Nie},
  booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
  year={2025},
  url={https://openreview.net/forum?id=tIW29IpCwG}
}