Skip to main content
Search

# Base-Guided Object-Category Restoration

1 related articles

Subscribe to updates
  1. arXiv

    Preference-optimized vision-language models say less and see less: early stopping of the base model reproduces 58% to 86% of their hallucination gain

    Four public preference-optimized checkpoints of LLaVA-1.5-7B lower object hallucination but also drop object recall on CHAIR-500 from 80.5 to between 65.1 and 76.2, with no significant set-level object F1 gain. Letting the base model stop earlier through a positive end-of-sequence logit bias until it matches each checkpoint's recall reproduces 58 to 86 percent of the CHAIRi gain of RLAIF-V, CHAIR-DPO and CSR on two disjoint 500-image COCO sets. Making the checkpoints write longer recovers only 2 to 9 percent of the lost recall, and 94 to 96 percent of the added object mentions repeat categories already named.

You’re all caught up