Preprint
Aug 2026
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
VARM-Bench provides an auditable and reproducible benchmark for evaluating verifiable moderation rationales in Chinese abusive-speech moderation, and shows that strong label-level performance can conceal substantial errors in complete moderation records.
Mingyu Yuan, Shengtao Wen, Lingbing Guo et al.
· 0 citations