Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts

• URL: http://arxiv.org/abs/2607.22479v1
• Date: Fri, 24 Jul 2026 16:47:57 GMT
• Title: Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts
• Abstract summary: This paper asks whether legal nuggets, defined as short and self-contained legal theses extracted from source documents, can improve dense retrieval over Brazilian legal collections.<n>We propose a pipeline that extracts nuggets from each document, indexes them with embeddings, retrieves nugget-level evidence, and aggregates the retrieved nuggets back to document-level rankings.
• Score: 6.120106694667796
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Legal retrieval over jurisprudential collections is challenging because court decisions are long, heterogeneous documents whose relevant legal thesis may occupy only a small portion of the text. This paper asks whether legal nuggets, defined as short and self-contained legal theses extracted from source documents, can improve dense retrieval over Brazilian legal collections. We propose a pipeline that extracts nuggets from each document, indexes them with embeddings, retrieves nugget-level evidence, and aggregates the retrieved nuggets back to document-level rankings. We evaluate this approach on four Portuguese legal retrieval benchmarks from the JUA ecosystem, reporting NDCG@10, MAP@10, and MRR@10. Nugget retrieval substantially improves the two jurisprudential datasets: on JUA-Juris, NDCG@10 increases from 0.10265 to 0.20461, and on JurisTCU from 0.20898 to 0.32696. However, it underperforms full-document retrieval on NormasTCU and BR-TaxQA, and an embedding-model ablation shows that strong domain-adapted retrievers can remain better in the full-document setting. The results demonstrate that legal nuggets can be useful for jurisprudence search, especially when queries are formulated as legal theses, but they may not transfer equally well to other legal retrieval scenarios.

Related papers

• JUÁ -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections [3.6360100966162787]
  Legal information retrieval in Portuguese remains difficult to evaluate systematically because available datasets differ widely in document type, query style, and relevance definition.<n>We present JU, a public benchmark for Brazilian legal retrieval designed to support more reproducible and comparable evaluation across heterogeneous legal collections.
  arXiv  Detail & Related papers  (2026-04-07T17:10:54Z)
• Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics [49.3262123849242]
  We introduce LEGIT (LEGal Issue Trees), a novel large-scale (24K instances) expert-level legal reasoning dataset.<n>We convert court judgments into hierarchical trees of opposing parties' arguments and the court's conclusions, which serve as rubrics for evaluating the issue coverage and correctness of the reasoning traces.
  arXiv  Detail & Related papers  (2025-11-30T18:32:43Z)
• Augmented Question-guided Retrieval (AQgR) of Indian Case Law with LLM, RAG, and Structured Summaries [0.0]
  This paper proposes the use of Large Language Models (LLMs) to facilitate the retrieval of relevant cases.<n>Our approach combines Retrieval Augmented Generation (RAG) with structured summaries optimized for Indian case law.<n>The system generates targeted legal questions based on factual scenarios to identify relevant case law more effectively.
  arXiv  Detail & Related papers  (2025-07-23T05:24:44Z)
• LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation [9.894351313663874]
  Legal Case Retrieval (LCR) is a fundamental task for legal professionals.<n>Existing studies on LCR face two major limitations.<n>First, they are evaluated on relatively small-scale retrieval corpora.<n>Second, their reliance on embedding-based or lexical matching methods often results in limited representations and legally irrelevant matches.
  arXiv  Detail & Related papers  (2025-05-28T09:02:41Z)
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval [54.54576644403115]
  We introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents.<n>Our dataset consists of 1,384 real-world queries spanning diverse domains, such as economics, psychology, mathematics, and coding.<n>We show that incorporating explicit reasoning about the query improves retrieval performance by up to 12.2 points.
  arXiv  Detail & Related papers  (2024-07-16T17:58:27Z)
• CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation [44.67578050648625]
  We transform a large open-source legal corpus into a dataset supporting information retrieval (IR) and retrieval-augmented generation (RAG) This dataset CLERC is constructed for training and evaluating models on their ability to (1) find corresponding citations for a given piece of legal analysis and to (2) compile the text of these citations into a cogent analysis that supports a reasoning goal.
  arXiv  Detail & Related papers  (2024-06-24T23:57:57Z)
• STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals [14.002280587675175]
  Statute retrieval aims to find relevant statutory articles for specific queries. Existing statute retrieval benchmarks focus on formal and professional queries from sources like bar exams and legal case documents. To address this gap, we introduce the STAtute Retrieval dataset (STARD) Unlike existing statute retrieval datasets, STARD captures the complexity and diversity of real queries from the general public.
  arXiv  Detail & Related papers  (2024-06-21T17:10:09Z)
• MUSER: A Multi-View Similar Case Retrieval Dataset [65.36779942237357]
  Similar case retrieval (SCR) is a representative legal AI application that plays a pivotal role in promoting judicial fairness. Existing SCR datasets only focus on the fact description section when judging the similarity between cases. We present M, a similar case retrieval dataset based on multi-view similarity measurement and comprehensive legal element with sentence-level legal element annotations.
  arXiv  Detail & Related papers  (2023-10-24T08:17:11Z)
• DAPR: A Benchmark on Document-Aware Passage Retrieval [57.45793782107218]
  We propose and name this task emphDocument-Aware Passage Retrieval (DAPR) While analyzing the errors of the State-of-The-Art (SoTA) passage retrievers, we find the major errors (53.5%) are due to missing document context. Our created benchmark enables future research on developing and comparing retrieval systems for the new task.
  arXiv  Detail & Related papers  (2023-05-23T10:39:57Z)
• SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval [75.05173891207214]
  Legal case retrieval plays a core role in the intelligent legal system. Most existing language models have difficulty understanding the long-distance dependencies between different structures. We propose a new Structure-Aware pre-traIned language model for LEgal case Retrieval.
  arXiv  Detail & Related papers  (2023-04-22T10:47:01Z)
• A Statutory Article Retrieval Dataset in French [4.082216579462797]
  We introduce the Belgian Statutory Article Retrieval dataset (BSARD) BSARD consists of 1,100+ French native legal questions labeled by experienced jurists with relevant articles from a corpus of 22,600+ Belgian law articles. We benchmark several unsupervised information retrieval methods based on term weighting and pooled embeddings. Our best performing baseline achieves 50.8% R@100, which is promising for the feasibility of the task and indicates that there is still substantial room for improvement.
  arXiv  Detail & Related papers  (2021-08-26T13:50:20Z)

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.