为金融大模型设计可审计的推理框架，让每条答案都有来源可查。
Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance
- 构建六阶段知识系统，用上下文感知检索追踪证据关系与可信度。
- 在145个金融问题上，正确率相近但可审计性显著提升。
- 适合需要合规溯源的金融、审计等高信任场景使用。
企业在金融领域采用大语言模型的障碍不在于语言流畅性，而在于信任：在财务规划与分析（FP&A）等受监管流程中，只有能追溯到权威来源并事后可审计的答案才可用。本文主张，企业金融领域的检索增强生成应以可审计性作为核心评价指标之一，并提出知识驱动分析框架（KDAF）。该框架通过六个迭代阶段构建本体驱动的知识系统，利用上下文感知相关性传播（CARP）检索证据，使每个检索事实均携带关系类型、置信度和来源链。在FinanceBench（145个问题）上的评估表明：零上下文推理正确率仅4.1%，而检索增强方法达10%-12%；各检索方法在答案正确率上无显著差异（如KDAF vs BM25：-0.007，95%CI [-0.021, 0.000]），但可审计性差异明显——KDAF在引用可追溯性F1上达0.515，优于无根基遍历+0.027（CI [0.006, 0.050]），优于BM25 +0.052（CI [0.024, 0.083]），区间均不含零。图结构检索无法引入问题主体外的证据（0/426项），而词法基线分别为16.8%和20.2%；所有选中项均具备完整出处链。因此，本研究认为，在金融场景中，可审计性才是本体增强检索值得投入的核心依据。
原文摘要 · Abstract (English)
Enterprise adoption of large language models in finance is constrained less by fluency than by trust: in Financial Planning and Analysis (FP&A) and other regulated workflows, an answer is usable only if it is traceable to authoritative sources and auditable after the fact. This paper argues that retrieval-augmented generation for enterprise finance should be evaluated on auditability alongside accuracy, and presents the Knowledge-Driven Analytics Framework (KDAF), which builds ontology-driven knowledge systems through six iterative stages and retrieves evidence via Context-Aware Relevance Propagation (CARP), so that every retrieved fact carries its relationship type, confidence, and source lineage. An evaluation on FinanceBench (145 questions) compares KDAF against zero-context inference, BM25, concept-weighted lexical retrieval, and ungrounded graph traversal. First, retrieval is necessary: zero-context inference reaches 4.1% correctness against 10-12% for retrieval-augmented conditions. Second, on answer correctness the retrieval conditions are statistically indistinguishable (KDAF vs BM25: -0.007, 95% CI [-0.021, 0.000]), so accuracy alone does not justify structured retrieval here -- a negative result we report explicitly. Third, on auditability the ordering reverses: KDAF attains the highest citation traceability F1 (0.515), exceeding ungrounded traversal by +0.027 (CI [0.006, 0.050]) and BM25 by +0.052 (CI [0.024, 0.083]), intervals excluding zero. Graph-structured retrieval also admits no evidence from outside the question subject entity (0 of 426 items, against 16.8% and 20.2% for lexical baselines), and every selected item resolves to a complete provenance chain. We argue that auditability, not accuracy, is the axis on which ontology-grounded retrieval earns its cost.
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。