LLM Digest
Subscribe

Story

arxiv_llm_reliability · Nov 17, 2026 · paper

Source brief

Say Less, Hallucinate Less? Diagnosing and Restoring Object Coverage in Preference-Optimized Vision-Language Models

arxiv.orgNov 17, 2026
original source linked

In brief

Preference optimization (PO) is the standard way to reduce object hallucination in large vision-language models. We find that four public PO checkpoints of LLaVA-1.5-7B also lower object coverage. They name fewer object categories, and their lower hallucination rates bring no sig

Feed lens
evaluation

Continue reading

Read the original at arxiv.org →Open in live feedRead that day’s brief

Earlier in this thread 4 items