research
Reading the Molecule Is Not Enough to Read the Reaction
RxnExBench separates molecular recognition from chemistry-aware reasoning across 3,565 annotated reactions and 26 structured fields.
Summary
RxnExBench separates molecular recognition from chemistry-aware reasoning across 3,565 annotated reactions and 26 structured fields.
Synthetic-chemistry papers often compress conditions and outcomes into dense screen tables and substrate-scope figures. RxnExBench turns 3,565 expert-annotated reactions and 2,361 structures into a schema with 15 roles and 26 core fields. An oracle protocol supplies molecular recognition so the evaluation can isolate higher-level multimodal reasoning. Across nine vision-language models, performance fell as schema complexity and reasoning demands increased; even with oracle molecules, integrating the figure and applying chemistry knowledge remained the bottleneck. The benchmark is drawn from selected journals and annotations, and the paper promises public release; it does not show safe autonomous extraction for all chemistry literature.
Why it matters
RxnExBench separates molecular recognition from chemistry-aware reasoning across 3,565 annotated reactions and 26 structured fields.
Limits and context
- The benchmark is drawn from selected journals and annotations, and the paper promises public release; it does not show safe autonomous extraction for all chemistry literature.
Key claims
RxnExBench separates molecular recognition from chemistry-aware reasoning across 3,565 annotated reactions and 26 structured fields.
Qualification: The benchmark is drawn from selected journals and annotations, and the paper promises public release; it does not show safe autonomous extraction for all chemistry literature.
Evidence: source-2026-10-26-012
Sources
- arXiv preprint 2610.32221, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.