README.md

Contextual Benchmarking Evaluation Code

This repo is using the following state of the art prompting strategies for benchmarking LLM-based judgement:

1. Input-Output Prompting
2. Chain-of-Thought Prompting (https://arxiv.org/pdf/2201.11903)
3. Chain-of-Thought + Self-Consistency Prompting (https://arxiv.org/pdf/2203.11171)
4. Multi Agent Debate (https://arxiv.org/pdf/2305.19118)
5. Multi Agent Roundtable (https://arxiv.org/pdf/2309.13007)