用结构化卡片提升金融文档问答的精准与可审计性
FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering
- 将财务证据选择转化为约束满足问题，基于实体、指标、周期等字段对齐
- 在两个基准上显著提升早期召回率，排名方差降低37%以上
- 无需微调模型，适合需要可解释性的金融分析场景
针对长篇企业文件中的金融问答任务，现有基于大模型的重排序方法主要优化语义相关性，导致排名不稳定且决策过程不透明。我们提出FinCards，一种基于结构化卡片的重排序框架，将财务证据选择重构为在金融感知模式下的约束满足问题。该框架通过实体、指标、期间和数值片段等对齐字段表示文件片段与问题，实现确定性的字段级匹配。证据选取采用多阶段锦标赛式重排序与稳定性感知聚合，生成可审计的决策轨迹。在两个企业文件问答基准上，FinCards显著优于基于词法和大模型的基线方法，提升了早期召回率并降低排名方差，且无需模型微调或不可预测的推理预算。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。