SWORD Benchmark

What is SWORD?

A benchmark of syntactically correct but factually incorrect statements across eight languages for evaluating multilingual factual error rejection.

Released

2026-09-08

Evaluates

Factuality, General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.09349

SWORD paper

• Paper https://arxiv.org/abs/2609.09349

Which sources cite SWORD?

• SWORD

Related Factuality, General AI, Language & Knowledge, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench