orcarouter/DeepSeek-V4.1-Flash-1017-abliterated-GGUF Text Generation • 748B • Updated about 11 hours ago • 9.02k • 231
Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments Paper • 2610.15634 • Published 16 days ago • 2