The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models 事件

REGULATION2026-06-05影响: MEDIUM

The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models arXiv:2606.05183v1 Announce Type: new Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode. We introduce the Granularity Gap: coarse binary metrics mask substantial social-compliance behaviors where models capitulate to user framing, validate questionable premises, or soften factual corrections withou