This repository provides prompts from the paper "JudgeBench: A Benchmark for Evaluating LLM-Based Judges" (https://arxiv.org/pdf/2410.12784) in easy-to-reuse YAML format.
TODO: add more detailed description and prompts
This repository provides prompts from the paper "JudgeBench: A Benchmark for Evaluating LLM-Based Judges" (https://arxiv.org/pdf/2410.12784) in easy-to-reuse YAML format.
TODO: add more detailed description and prompts