It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
Very large language models (LLMs) such as GPT-4 have shown the ability to handle complex tasks by generating and self-refining …
PDF Cite Code
It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation