SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation

TL;DR

SciFIBench is a new benchmark with 2000 questions designed to evaluate large multimodal models' ability to interpret scientific figures, revealing their current limitations and guiding future improvements.

Contribution

The paper introduces SciFIBench, a comprehensive benchmark for scientific figure interpretation, and evaluates 28 models, highlighting their challenges and assessing reasoning faithfulness.

Findings

28 LMMs find SciFIBench challenging

Benchmark reveals gaps in models' interpretative abilities

Assessment of alignment and reasoning faithfulness

Abstract

Large multimodal models (LMMs) have proven flexible and generalisable across many tasks and fields. Although they have strong potential to aid scientific research, their capabilities in this domain are not well characterised. A key aspect of scientific research is the ability to understand and interpret figures, which serve as a rich, compressed source of complex information. In this work, we present SciFIBench, a scientific figure interpretation benchmark consisting of 2000 questions split between two tasks across 8 categories. The questions are curated from arXiv paper figures and captions, using adversarial filtering to find hard negatives and human verification for quality control. We evaluate 28 LMMs on SciFIBench, finding it to be a challenging benchmark. Finally, we investigate the alignment and reasoning faithfulness of the LMMs on augmented question sets from our benchmark. We release SciFIBench to encourage progress in this domain.