conftrace_

self-recognition capability

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

self-preference bia (1) evaluation alignment (1) controlled experiment (1) evaluation bia (1) large language model (1) unbiased evaluation (1) ai safety (1) llm evaluation (1) reward modeling (1)

Papers

LLM Evaluators Recognize and Favor Their Own Generations NeurIPS 2024