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

Avshalom Manevich, Reut Tsarfaty

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Large Vision-Language Models (LVLMs) are an extension of Large Language Models (LLMs) that facilitate processing both image and text inputs, expanding AI capabilities. However, LVLMs struggle with object hallucinations due to their reliance on text cues and learned object co-occurrence biases. While most research quantifies these hallucinations, mitigation strategies are still lacking. Our study introduces a Language Contrastive Decoding (LCD) algorithm that adjusts LVLM outputs based on LLM distribution confidence levels, effectively reducing object hallucinations. We demonstrate the advantages of LCD in leading LVLMs, showing up to 4% improvement in POPE F1 scores and up to 36% reduction in CHAIR scores on the COCO validation set, while also improving captioning quality scores. Our method effectively improves LVLMs without needing complex post-processing or retraining, and is easily applicable to different models. Our findings highlight the potential of further exploration of LVLM-specific decoding algorithms for improved multimodal performance.

Original languageEnglish
Title of host publication62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 - Proceedings of the Conference
EditorsLun-Wei Ku, Andre Martins, Vivek Srikumar
PublisherAssociation for Computational Linguistics (ACL)
Pages6008-6022
Number of pages15
ISBN (Electronic)9798891760998
StatePublished - 2024
Externally publishedYes
EventFindings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 - Hybrid, Bangkok, Thailand
Duration: 11 Aug 202416 Aug 2024

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

ConferenceFindings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024
Country/TerritoryThailand
CityHybrid, Bangkok
Period11/08/2416/08/24

Bibliographical note

Publisher Copyright:
© 2024 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of 'Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)'. Together they form a unique fingerprint.

Cite this