CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language Models
This work addresses the need for more robust evaluation benchmarks in VLM research, though it is incremental as it builds on existing methods.
The paper tackles the problem of evaluating Vision-Language Models (VLMs) by analyzing existing methods and introducing CHIRP, a new benchmark for open-ended response evaluation, along with the Robin model suite to identify limitations and promote reproducibility.
The proliferation of Vision-Language Models (VLMs) in the past several years calls for rigorous and comprehensive evaluation methods and benchmarks. This work analyzes existing VLM evaluation techniques, including automated metrics, AI-based assessments, and human evaluations across diverse tasks. We first introduce Robin - a novel suite of VLMs that we built by combining Large Language Models (LLMs) and Vision Encoders (VEs) at multiple scales, and use Robin to identify shortcomings of current evaluation approaches across scales. Next, to overcome the identified limitations, we introduce CHIRP - a new long form response benchmark we developed for more robust and complete VLM evaluation. We provide open access to the Robin training code, model suite, and CHIRP benchmark to promote reproducibility and advance VLM research.