Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law

• URL: http://arxiv.org/abs/2608.09393v1
• Date: Mon, 10 Aug 2026 10:20:13 GMT
• Title: Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law
• Abstract summary: We identify and quantify temporal misgrounding: the systematic retrieval and citation of the currently in-force version of a legal article.<n>We introduce FiscalQA Pro, pairing a versioned corpus of 32,436 article-versions of the French tax code with an all-model-hard temporal-reasoning track.<n>Our end-to-end retriever over a multi-version index, with no oracle, reaches 98.3% mean strict.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• Annotated Surrogate Retrieval for Polish Statutory Law [0.0]
  We present a family of retrieval methods for Polish statutory law built on document surrogates.<n>ASCR is a surrogate cascade with reranking; ASCR-H fuses a dense list into that cascade; and DTF replaces both language-model stages with three lexical and dense retrievers.<n>We evaluate all three against fourteen lexical, dense, fused and ablated baselines plus four controls, on 300 questions from the 2024 and 2025 Polish bar and legal counsel entrance examinations.
  arXiv  Detail & Related papers  (2026-08-31T15:05:00Z)
• Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding [3.285110528753401]
  Evolving documents, such as laws, tax codes, and software documentation, are amended, replaced, and sometimes reverted over time.<n>We present TIDE, an expert-verified benchmark of 3,050 QA pairs over 644 official customs instruments issued by the Government of Bangladesh.
  arXiv  Detail & Related papers  (2026-08-09T06:17:41Z)
• When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responses [1.5770673503612611]
  Memory-augmented agents can know that a user's stored state is outdated and still plan around the old value.<n>We identify one structural contributor: draft-anchored verification checks what a response says, and in an open-ended response the stale dependency is usually unsaid.
  arXiv  Detail & Related papers  (2026-08-03T02:49:08Z)
• From Attack Simulation to SIEM Rule: Deterministic Detection-as-Code Synthesis with Probe-Level Traceability [51.56484100374058]
  Security teams simulate attacks against their own systems to check whether their monitoring would catch a real intruder.<n>A human bridges that gap by hand, reading each finding and writing the corresponding Sigma rule.<n>We show this translation can be partially automated when probes are drawn from a locked corpus.
  arXiv  Detail & Related papers  (2026-06-03T14:26:25Z)
• How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings [56.70440596502351]
  The past year has seen over 20 open document parsing models, yet benchmarks almost exclusively on OmniDocBench.<n>We present PureDocBench, a benchmark thatrenders document images from HTML/CSS, covering 10 domains, 66 pages, and 1,475 pages.
  arXiv  Detail & Related papers  (2026-05-08T09:30:31Z)
• ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search [49.61286310968402]
  We introduce ARGOS, the first benchmark and framework that reformulates multi-camera person search as an interactive reasoning problem.<n>An ARGOS agent receives a vague witness statement and must decide what to ask, when to invoke spatial or temporal tools, and how to interpret ambiguous responses.<n>The benchmark comprises 2,691 tasks across 14 real-world scenarios in three progressive tracks: semantic perception (Who), spatial reasoning (Where), and temporal reasoning (When)
  arXiv  Detail & Related papers  (2026-04-14T14:06:19Z)
• Still Fresh? Evaluating Temporal Drift in Retrieval Benchmarks [40.92390378341581]
  temporal changes in technical corpora, such as API deprecations and code reorganizations, can render existing benchmarks stale.<n>We examine two independent corpus snapshots of FreshStack from October 2024 and October 2025 to answer questions about LangChain.
  arXiv  Detail & Related papers  (2026-03-04T19:18:11Z)
• Recon, Answer, Verify: Agents in Search of Truth [36.56689822791777]
  We present Politi Fact Only (PFO), a benchmark dataset of 2,982 political claims from politifact.com.<n>All post claim analysis and annotator cues have been removed manually.<n>We propose RAV, an agentic framework with three agents: question generator, answer generator, and label generator.
  arXiv  Detail & Related papers  (2025-07-04T15:44:28Z)
• LEXam: Benchmarking Legal Reasoning on 340 Law Exams [76.3521146499006]
  We introduce textscLEXam, a novel benchmark derived from 340 law exams spanning 116 law school courses across a range of subjects and degree levels.<n>The dataset comprises 4,886 law exam questions in English and German, including 2,841 long-form, open-ended questions and 2,045 multiple-choice questions.<n>Our results underscore the effectiveness of the dataset in differentiating between models with varying capabilities.
  arXiv  Detail & Related papers  (2025-05-19T08:48:12Z)
• IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions [54.23087908182134]
  We introduce the first large-scale counterfactual open-domain question-answering (QA) benchmarks, named IfQA. The IfQA dataset contains over 3,800 questions that were annotated by crowdworkers on relevant Wikipedia passages. The unique challenges posed by the IfQA benchmark will push open-domain QA research on both retrieval and counterfactual reasoning fronts.
  arXiv  Detail & Related papers  (2023-05-23T12:43:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.