Summary of V-dpo: Mitigating Hallucination in Large Vision Language Models Via Vision-guided Direct Preference Optimization, by Yuxi Xie et al.
V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
by Yuxi Xie, Guanzhen Li, Xiao Xu, Min-Yen Kan
First submitted to arxiv on: 5 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles the issue of hallucination in large vision-language models (LVLMs), which misalign their textual responses with visual content. The researchers identify the LLM backbone as a primary cause of this problem, introducing language-based bias and neglecting visual context. To mitigate these effects, the authors propose a novel approach that addresses the imbalance between language priors and visual inputs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large vision-language models (LVLMs) have a problem called hallucination, where they don’t accurately match what they see with what they say. This happens because LVLMs rely too much on their Large Language Model (LLM) part, which makes them biased towards language and not enough towards the pictures they’re looking at. The authors of this paper want to fix this by coming up with a new way to make LVLMs pay more attention to what they see. |
Keywords
» Artificial intelligence » Attention » Hallucination » Large language model
