Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)

Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD) Avshalom Manevich author Reut Tsarfaty author 2024-08 text Findings of the Association for Computational Linguistics: ACL 2024 Lun-Wei Ku editor Andre Martins editor Vivek Srikumar editor Association for Computational Linguistics Bangkok, Thailand conference publication manevich-tsarfaty-2024-mitigating 10.18653/v1/2024.findings-acl.359 https://aclanthology.org/2024.findings-acl.359/ 2024-08 6008 6022