Self-Improving VLM Judges Without Human Annotations

Inna Wanyin Lin, Yushi Hu, Shuyue Stella Li, Scott Geng, Pang Wei Koh, Luke Zettlemoyer, Tim Althoff, Marjan Ghazvininejad

Keywords: VLM, LLM-as-a-Judge, VLM-as-a-Judge, Reward Models, Self Improvement

TL;DR: We propose a human-annotation-free, self-training framework that produces a strong VLM judge outperforming much larger models.

Abstract:

Effective judges of Vision-Language Models (VLMs) are crucial for model development. Current methods for training VLM judges mainly rely on large-scale human preference annotations. However, such an approach is costly, and the annotations easily become obsolete as models rapidly improve. In this work, we present a framework to self-train a VLM judge model without any human preference annotations, using only self-synthesized data. Our method is iterative and has three stages:
(1) generate diverse multimodal instruction-response pairs at varying quality levels, (2) generate reasoning traces and judgments for each pair, removing the ones that do not match our expected quality levels, and (3) training on correct judge answers and their reasoning traces. We evaluate the resulting judge on Multimodal RewardBench and VL-RewardBench across domains: correctness, preference, reasoning, safety, and visual question-answering. Our method improves a Llama-3.2-11B multimodal judge from 0.38 to 0.51 in overall accuracy on VL-RewardBench, often outperforming much larger models including Llama-3.2-90B, GPT-4o, and Claude 3.5 Sonnet, with strong gains in general, hallucination, and reasoning dimensions.
The strength of these human-annotation-free results suggest the potential for a future self-judge that evolves alongside rapidly improving VLM capabilities.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 101