ClaimDB: A Fact Verification Benchmark over Large Structured Data

TL;DR

ClaimDB introduces a large-scale fact verification benchmark over structured data, highlighting the challenges for current models in reasoning and abstention, and providing a new resource for advancing fact-checking research.

Contribution

This work presents ClaimDB, a comprehensive benchmark with real-world databases for evaluating fact verification methods over structured data, and analyzes the performance of state-of-the-art LLMs.

Findings

Over half of the models score below 55% accuracy.

Models struggle with abstention, admitting lack of evidence.

The benchmark and leaderboard are publicly released.

Abstract

Real-world fact-checking often involves verifying claims grounded in structured data at scale. Despite substantial progress in fact-verification benchmarks, this setting remains largely underexplored. In this work, we introduce ClaimDB, a fact-verification benchmark where the evidence for claims is derived from compositions of millions of records and multiple tables. ClaimDB consists of 80 unique real-life databases covering a wide range of domains, from governance and healthcare to media, education and the natural sciences. At this scale, verification approaches that rely on "reading" the evidence break down, forcing a timely shift toward reasoning in executable programs. We conduct extensive experiments with 30 state-of-the-art proprietary and open-source (below 70B) LLMs and find that more than half score below 55% accuracy. Our analysis also reveals that both closed- and open-source models struggle with abstention -- the ability to admit that there is no evidence to decide -- raising doubts about their reliability in high-stakes data analysis tasks. We release the benchmark, code, and the LLM leaderboard at https://claimdb.github.io .