VeriSpeak Benchmark

What is VeriSpeak?

A probe benchmark for speech-based fact verification in Large Audio Language Models, derived from KVQA and Wikidata, with synthetic false claims and veracity…

Released

2026-09-24

Evaluates

General AI, Information retrieval, Speech & Audio, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.30227

VeriSpeak paper and dataset

• Paper https://arxiv.org/abs/2609.30227
• Dataset https://huggingface.co/datasets/abhiram4572/VeriSpeak

Which sources cite VeriSpeak?

• VeriSpeak

Related General AI, Information retrieval, Speech & Audio, cs.LG benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench