法律问答中时间错位严重，新旧法版本混淆导致错误答案。
Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law
- 构建带时间版本的法国税法语料库，解决法律检索的时间依赖性问题。
- 静态检索模型正确率仅2.7%，而动态版本检索达98.3%准确率。
- 适合法律AI研究者、司法科技开发者及合规系统设计者参考。
我们识别并量化了法律RAG中的时间错位现象：在应适用历史或未来版本法律时，系统却检索并引用当前有效版本。标准法律RAG将语料视为静态，而我们认为法律问答本质上是时序索引检索问题。为此提出FiscalQA Pro，包含32,436个法国税法条文版本（1938–2031年共93年），搭配一个全模型难度的时序推理评测集：覆盖33个CGI条款的209道专家评审、可评分问题（221个发布；12个标记为不可回答）。在选择阶段，任何评估模型在四次采样中均未闭卷找回时间匹配的答案，且当前有效文本对除一题外所有问题均无正确答案。答案通过原子级真值“碎片”（正则与数值容差）严格评分，避免使用大模型作为裁判以防止继承时间偏差。十一模型测试中（五种前沿闭源系统+Gemini 2.5 Pro替代，五种开源模型），参数化知识平均严格准确率3.0%，静态当前版本RAG为2.7%。静态RAG零次召回适用版本，自信引用真实但不适用的内容。端到端多版本索引检索器无需人工标注即达98.3%平均严格准确率；若假设已知正确条文，可达99.1%，说明残余误差源于初始召回，非版本选择。此外，我们还发布了一个含69,208条引用链接的版本感知判例数据集，连同语料库、基准、模型输出和代码流程。
原文摘要 · Abstract (English)
We identify and quantify temporal misgrounding: the systematic retrieval and citation of the currently in-force version of a legal article when the applicable version is an earlier or future one. Standard legal RAG treats the corpus as static; we argue legal question answering is a temporally-indexed retrieval problem. We introduce FiscalQA Pro, pairing a versioned corpus of 32,436 article-versions of the French tax code (93 years, 1938-2031) with an all-model-hard temporal-reasoning track: 209 scored, expert-reviewed questions across 33 CGI articles (221 released; twelve flagged out of the answerable scope). At selection time, no evaluated model recovered its date-applicable answer closed-book in any of four sampling draws, and the currently in-force text lacks the gold value for all but one of the scored questions. Answers are scored deterministically via atomic ground-truth "nuggets" (regex and numeric-with-tolerance), never LLM-as-judge: an LLM judge would inherit the temporal bias it is meant to score. Across eleven models (five frontier closed-API systems plus Gemini 2.5 Pro as a substitute entry, and five open-weight), parametric knowledge yields 3.0% mean strict accuracy and RAG over a static current-version corpus 2.7%. Static RAG retrieves the date-applicable version 0% of the time, confidently citing a real but inapplicable version. Our end-to-end retriever over a multi-version index, with no oracle, reaches 98.3% mean strict; an oracle-article ablation reaches 99.1%, locating the residual gap in first-stage recall, not version selection. We additionally release a version-aware jurisprudence dataset of 69,208 citation links, together with the corpus, benchmark, model responses, and pipeline code.
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。