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

arXiv: https://arxiv.org/abs/2608.09393 · HTML: https://mlsanity.com/paper/2608.09393/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain](https://mlsanity.com/paper/2301.13126/) (2023)
- [LEXam: Benchmarking Legal Reasoning on 340 Law Exams](https://mlsanity.com/paper/2505.12864/) (2025)
- [OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning](https://mlsanity.com/paper/2603.08655/) (2026)
- [JuriBERT: A Masked-Language Model Adaptation for French Legal Text](https://mlsanity.com/paper/2110.01485/) (2021)
- [It's High Time: A Survey of Temporal Question Answering](https://mlsanity.com/paper/2505.20243/) (2025)
- [LexTime: A Benchmark for Temporal Ordering of Legal Events](https://mlsanity.com/paper/2506.04041/) (2025)
- [Fine-grained Claim-level RAG Benchmark for Law](https://mlsanity.com/paper/2605.21071/) (2026)
- [Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning](https://mlsanity.com/paper/2605.25920/) (2026)
- [Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question Answering](https://mlsanity.com/paper/2605.23497/) (2026)

## Abstract (arXiv)

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.