FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringSimilar Papers 제목 키워드 기반
Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis
Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a Retrieval-Augmented Generation (RAG) system designed to answer question…
Semantic RetrievalBeyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting
Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages and multiple languages. Standard Retrieval-Augmented Generation (RAG)…
Semantic SimilarityFAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations
The continuous growth of the e-commerce industry attracts fraudsters who exploit stolen credit card details. Companies often investigate suspicious transactions in order to retain customer trust and address gaps in their…
Fraud DetectionLanguage ModelingLanguage ModellingLarge Language ModelInteractive Model Cards: A Human-Centered Approach to Model Documentation
Deep learning models for natural language processing (NLP) are increasingly adopted and deployed by analysts without formal training in NLP or machine learning (ML). However, the documentation intended to convey the mode…
EthicsmodelTHaLLE: Text Hyperlocally Augmented Large Language Extension -- Technical Report
Recent advancements in Large Language Models (LLMs) have revealed new capabilities and opportunities across the technological landscape. However, the practicality of very large LLMs is challenged by their high compute co…
Financial Analysis