CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Putta, Akshith Reddy, Devasier, Jacob, Li, Chengkai
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918454320168960
author Putta, Akshith Reddy
Devasier, Jacob
Li, Chengkai
author_facet Putta, Akshith Reddy
Devasier, Jacob
Li, Chengkai
contents Automated Fact-Checking has largely focused on verifying general knowledge against static corpora, overlooking high-stakes domains like law where truth is evolving and technically complex. We introduce CaseFacts, a benchmark for verifying colloquial legal claims against U.S. Supreme Court precedents. Unlike existing resources that map formal texts to formal texts, CaseFacts challenges systems to bridge the semantic gap between layperson assertions and technical jurisprudence while accounting for temporal validity. The dataset consists of 6,294 claims categorized as Supported, Refuted, or Overruled. We construct this benchmark using a multi-stage pipeline that leverages Large Language Models (LLMs) to synthesize claims from expert case summaries, employing a novel semantic similarity heuristic to efficiently identify and verify complex legal overrulings. Experiments with state-of-the-art LLMs reveal that the task remains challenging; notably, augmenting models with unrestricted web search degrades performance compared to closed-book baselines due to the retrieval of noisy, non-authoritative precedents. We release CaseFacts to spur research into legal fact verification systems.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17230
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval
Putta, Akshith Reddy
Devasier, Jacob
Li, Chengkai
Computation and Language
Machine Learning
Automated Fact-Checking has largely focused on verifying general knowledge against static corpora, overlooking high-stakes domains like law where truth is evolving and technically complex. We introduce CaseFacts, a benchmark for verifying colloquial legal claims against U.S. Supreme Court precedents. Unlike existing resources that map formal texts to formal texts, CaseFacts challenges systems to bridge the semantic gap between layperson assertions and technical jurisprudence while accounting for temporal validity. The dataset consists of 6,294 claims categorized as Supported, Refuted, or Overruled. We construct this benchmark using a multi-stage pipeline that leverages Large Language Models (LLMs) to synthesize claims from expert case summaries, employing a novel semantic similarity heuristic to efficiently identify and verify complex legal overrulings. Experiments with state-of-the-art LLMs reveal that the task remains challenging; notably, augmenting models with unrestricted web search degrades performance compared to closed-book baselines due to the retrieval of noisy, non-authoritative precedents. We release CaseFacts to spur research into legal fact verification systems.
title CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2601.17230