Introduces FURINA-Builder, a scalable multi-agent pipeline that constructs fully customizable role-playing benchmarks, and releases FURINA-Bench with evaluations showing reasoning models trade performance for increased hallucinations.
Are you sure this is the only way? What made you so confident it’ll work?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline
Introduces FURINA-Builder, a scalable multi-agent pipeline that constructs fully customizable role-playing benchmarks, and releases FURINA-Bench with evaluations showing reasoning models trade performance for increased hallucinations.