E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

Researchers introduced E2A-Bench, a new benchmark for measuring evidence-to-action reliability in financial chart reasoning by vision-language models (VLMs). The benchmark targets a gap in existing hallucination evaluations, which the authors characterize as mostly claim-centric: they assess whether generated statements are supported but not whether evidence remains traceable through rationale, confidence, and final action recommendations.

Can financial vision-language models VLMs turn chart evidence into reliable action recommendations? Existing hallucination evaluations are mostly claim-centric; they assess whether generated statements are supported, but not whether evidence remains traceable through rationale, confidence, and fin