What Does Hard-Negative Fine-Tuning Teach Multimodal Large Language Models? Controlled Evidence from a Compositional Benchmark
Fine-tuning on hard negatives is a popular way to improve the compositional reasoning of vision-language models, but when accuracy goes up it is rarely clear what the model actually learned. We ask this question for multimodal large language models.
By Ranjith ChodavarapuarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 17, 2026.
Comments
Sign in to join the discussion.