ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models

Park et al. "ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I6.32689

[Park et al. "ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/park2025aaai-convis/) doi:10.1609/AAAI.V39I6.32689

@inproceedings{park2025aaai-convis,
  title     = {{ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models}},
  author    = {Park, Yeji and Lee, Deokyeong and Choe, Junsuk and Chang, Buru},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {6434-6442},
  doi       = {10.1609/AAAI.V39I6.32689},
  url       = {https://mlanthology.org/aaai/2025/park2025aaai-convis/}
}