FinCARDS: 基于卡片的分析师重排序用于财务文档问答
FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering
AI总结：
FinCARDS通过结构化重排序框架，将财务证据选择转化为在财务意识模式下的约束满足问题，提升长文档问答的稳定性与可追溯性。
摘要：
财务长文档问答需要证据满足严格实体、财务指标、财政时期和数值约束。然而，现有基于LLM的重排序器主要优化语义相关性，导致排名不稳定且决策不透明。我们提出FinCards，一种结构化重排序框架，将财务证据选择重新表述为在财务意识模式下的约束满足问题。FinCards通过对齐的模式字段（实体、指标、时期和数值跨度）表示文件片段和问题，实现确定性的字段级匹配。证据通过多阶段锦标赛重排序和稳定性感知聚合选择，生成可审计的决策轨迹。在两个企业文件问答基准测试中，FinCards显著提升了早期排名检索性能，优于基于词法和LLM的重排序基线，同时减少排名方差，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。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
