all AI news
Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
March 26, 2024, 4:47 a.m. | Minchan Kim, Minyeong Kim, Junik Bae, Suhwan Choi, Sungkyung Kim, Buru Chang
cs.CV updates on arXiv.org arxiv.org
Abstract: Hallucinations in vision-language models pose a significant challenge to their reliability, particularly in the generation of long captions. Current methods fall short of accurately identifying and mitigating these hallucinations. To address this issue, we introduce ESREAL, a novel unsupervised learning framework designed to suppress the generation of hallucinations through accurate localization and penalization of hallucinated tokens. Initially, ESREAL creates a reconstructed image based on the generated caption and aligns its corresponding regions with those of …
abstract arxiv captions challenge cs.cl cs.cv current framework hallucinations issue language language models novel reliability semantic type unsupervised unsupervised learning vision vision-language models
More from arxiv.org / cs.CV updates on arXiv.org
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
1 day, 19 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Director, Clinical Data Science
@ Aura | Remote USA
Research Scientist, AI (PhD)
@ Meta | Menlo Park, CA | New York City