Researcher观点: Why Worst-of-N might be the one true metric for LLMs
willdepue · x · 2026-08-31
The post highlights a perspective from researcher Joanne Jang, arguing that 'worst-of-n'—sampling and evaluating the poorest outputs—is a more critical metric for LLM reliability than 'best-of-n'. This观点 challenges current optimization strategies focused solely on peak performance.
More from Research
- Book recommendation: Mathematics of Machine Learning — techNmak · 2026-08-31
- S1's ICL advantage grows exponentially in long-horizon, out-of-distribution tasks — ZeYanjie · 2026-08-31
- Robot control trained in under 2 minutes on one 4090 via Sim2Sim transfer — yacineMTB · 2026-08-31
- Gumbel-Softmax Watermark Variant Can Hide LLM's True CoT Cryptographically — sytelus · 2026-08-31
- Long CoT may not need single model call — CShorten30 · 2026-08-31
- Non-technical explanation of Gaussian Splatting technology — CSProfKGD · 2026-08-31