AI RESEARCH
FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering
arXiv CS.AI
•
ArXi:2601.06992v2 Announce Type: replace-cross Financial question answering (QA) over long corporate filings requires evidence to satisfy strict constraints on entities, financial metrics, fiscal periods, and numeric values. However, existing LLM-based rerankers primarily optimize semantic relevance, leading to unstable rankings and opaque decisions on long documents. We propose FinCards, a structured reranking framework that reframes financial evidence selection as constraint satisfaction under a finance-aware schema.