Evaluating Bias in Chinese Large Language Models across Tasks and Registers: Task Operationalization Effects and Irony Classification Risks

arXiv:2610.14464v1 Announce Type: new Abstract: In Chinese content governance, large language models are increasingly used to identify toxic and discriminatory expressions, yet both task operationalization and ironic expression can alter bias measurement readings. We conducted a preregistered multi-

arXiv cs.CLMittwoch 06:00 · 14.10.1 Min. Lesezeit