scientific-claim-verification

This paper presents HNR-DAC, a two-stage framework for scientific claim verification over cited papers, combining hard-negative reranking and distribution-aligned classification. It achieves strong results on NLPCC 2026 Task 10 Track 2, ranking third on the leaderboard with the highest Macro-F1.

This paper introduces ToolSciVer, the first tool-augmented framework for multimodal scientific claim verification (MSCV), which equips a VLM with type-aware visual tools and trains the policy using GRPO to achieve superior performance on SciVer and MuSciClaims datasets across multiple model families.