[ICML 2025] SECOND: Mitigating Perceptual Hallucination in VLMs via Selective and Contrastive Decoding
This repository provides the official PyTorch implementation of the following paper:
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
📄 Paper (arXiv)
🌐 Project Page
Clone the repository and install dependencies:
cd SECOND/lmms-eval-vicuna
pip install -e .
cd LLaVA-NeXT
pip install -e .Run SECOND with the provided scripts:
cd SECOND/lmms-eval-vicuna
./run.shIf you find this work useful, please consider citing:
@inproceedings{park2025second,
title = {SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding},
author = {Park, Woohyeon and Kim, Woojin and Kim, Jaeik and Do, Jaeyoung},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning (ICML)},
year = {2025},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR}
}