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：金融问答任务需从长篇企业财报中提取证据，以满足对实体、财务指标、会计期间及数值的严格约束。然而，现有基于大语言模型的重排序方法主要优化语义相关性，导致长文档排序结果不稳定且决策过程不透明。本文提出FinCards结构化重排序框架，将金融证据选择问题重新定义为在金融感知模式下的约束满足问题。该框架利用对齐后的模式字段（实体、指标、会计期间和数值跨度）表示文档块与问题，实现确定性字段级匹配。通过多阶段锦标赛式重排序结合稳定性感知聚合策略进行证据选择，生成可审计的决策轨迹。在两个企业财报问答基准测试中，FinCards在不需模型微调或不可预测推理预算的情况下，相较于基于词法和LLM的重排序基线，显著提升了早期排序召回率，同时降低了排序方差。本论文代码已开源：https://github.com/XanderZhou2022/FINCARDS