Abstract
Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and textual context. However, existing methods often fail because they struggle to locate decisive visual evidence, accurately read structured scientific visuals, and integrate multimodal observations into reliable reasoning.
We introduce ToolSciVer, the first tool-augmented framework for MSCV to our knowledge. ToolSciVer equips a Visual Language Model (VLM) with three type-aware visual tools: table row/column focus, chart-to-structure parsing, and high-resolution region zoom. These tools convert dense scientific visuals into explicit, claim-facing evidence.
The framework trains the policy with Group Relative Policy Optimization (GRPO) under a composite reward of answer correctness, format validity, length control, tool-use efficiency, and tool-validity penalties.
Experiments on SciVer and MuSciClaims datasets on five VLMs from three model families (Qwen, InternVL, Gemma) demonstrate that our method achieves superior performance compared to four competitive baselines, including prompting-based and RL-based tool-use methods, highlighting the effectiveness of learned, type-aware tool use for scientific claim verification.
Blogger's Review: ToolSciVer enhances the accuracy of scientific claim verification by introducing type-aware visual tools. This approach not only addresses the shortcomings of traditional methods in handling multimodal data but also provides new insights for future scientific research, making it a noteworthy development.