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. FinCards represents filing chunks and questions using aligned schema fields (entities, metrics, periods, and numeric spans), enabling deterministic field-level matching. Evidence is selected via a multi-stage tournament reranking with stability-aware aggregation, producing auditable decision traces. Across two corporate filing QA benchmarks, FinCards substantially improves early-rank retrieval over both lexical and LLM-based reranking baselines, while reducing ranking variance, without requiring model fine-tuning or unpredictable inference budgets. Our code is available at https://github.com/XanderZhou2022/FINCARDS.

翻译：针对长篇公司文件的金融问答需要证据满足实体、财务指标、会计期间和数值的严格约束。然而，现有的基于大语言模型的重排序器主要优化语义相关性，导致在长文档上的排序不稳定且决策不透明。我们提出了FinCards，一种结构化重排序框架，将金融证据选择重新定义为在金融感知模式下的约束满足问题。FinCards使用对齐的模式字段（实体、指标、期间和数值跨度）来表示文件片段和问题，从而实现确定性的字段级匹配。证据通过具有稳定性感知聚合的多阶段锦标赛重排序进行选择，并生成可审计的决策轨迹。在两个公司文件问答基准测试中，FinCards在早期排序检索上显著优于基于词法和基于大语言模型的重排序基线，同时降低了排序方差，且无需模型微调或不可预测的推理预算。我们的代码可在 https://github.com/XanderZhou2022/FINCARDS 获取。