iLearn-Lab/NeurIPS25-SymMPO
收藏资源简介：
--- license: apache-2.0 --- <div align="center"> <h2 align="center"> <b>SymMPO: Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization</b> </h2> <a target="_blank" href="https://github.com/Liuwq-bit">Wenqi Liu</a><sup>1</sup>, <a target="_blank" href="https://scholar.google.com/citations?user=29gP4okAAAAJ">Xuemeng Song</a><sup>2</sup>, <a target="_blank" href="https://scholar.google.com/citations?user=tvPOeFQAAAAJ">Jiaxi Li</a><sup>3</sup>, <a target="_blank" href="https://scholar.google.com/citations?user=im-bS2YAAAAJ">Yinwei Wei</a><sup>1</sup>, <a target="_blank" href="https://scholar.google.com/citations?user=VWunnXEAAAAJ">Zheng Na</a><sup>4</sup>, <a target="_blank" href="https://scholar.google.com/citations?user=aZZfn90AAAAJ">Jianhua Yin</a><sup>1</sup>, <a target="_blank" href="https://scholar.google.com/citations?user=yywVMhUAAAAJ">Liqiang Nie</a><sup>5</sup> <br> <sup>1</sup>Shandong University    <sup>2</sup>Southern University of Science and Technology    <sup>3</sup>University of Georgia    <br> <sup>4</sup>National University of Singapore    <sup>5</sup>Harbin Institute of Technology, Shenzhen    <br /> <a href='https://arxiv.org/abs/2506.11712'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> <a href='https://huggingface.co/iLearn-Lab/NeurIPS25-SymMPO-7B'><img src='https://img.shields.io/badge/Model-7B-yellow'></a> <a href='https://huggingface.co/iLearn-Lab/NeurIPS25-SymMPO-13B'><img src='https://img.shields.io/badge/Model-13B-yellow'></a> <a href='https://huggingface.co/datasets/iLearn-Lab/NeurIPS25-SymMPO'><img src='https://img.shields.io/badge/Dataset-HF-blue'></a> </div> --- ## 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](https://github.com/haotian-liu/LLaVA). ## Citation If you find our work helpful, please consider citing: ```bibtex @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} } ```
