FORGE Benchmark

What is FORGE?

FORGE evaluates whether search-augmented language models recommend fake products introduced through controlled modifications to retrieved web pages.

Released

2026-06-11

Evaluates

Cybersecurity, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.13610

FORGE paper and code

• Paper https://arxiv.org/abs/2606.13610
• Code https://github.com/leoluolol/forge-benchmark

Which sources cite FORGE?

• FORGE

Related Cybersecurity, Language & Knowledge, cs.CL benchmarks

• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• ActiveSciBench
• AdaMem-Bench
• AdaPlanBench
• AdvancedMathBench