SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation
This work addresses the need to characterize LMM capabilities for scientific research, specifically in interpreting figures, which is an incremental step in benchmarking.
The authors tackled the problem of evaluating large multimodal models (LMMs) for scientific figure interpretation by introducing SciFIBench, a benchmark with 2000 questions across 8 categories, finding it challenging for 28 tested LMMs.
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.