In this paper, we break down the self-correction process into two core components: mistake finding and output correction.

Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning.

You can also check exclusive content about #llms, #llm-mistake-finding, #llm-output-correction, #big-bench-mistake, #chain-of-thought, #nlp, #self-consistency, #zero-shot-prompting, and more.

This story was written by: @textmodels. Learn more about this writer by checking @textmodels's about page,

and for more stories, please visit hackernoon.com.

Large Language Models (LLMs) have dominated the field of NLP in recent years. LLMs have demonstrated the ability to solve tasks with zero- or few-shot prompting. Recent literature has focused on the concept of self-correction, i.e. having an LLM correct its own outputs. Attempts to self-correct logical or reasoning errors often cause correct answers to become incorrect, resulting in worse performances overall. In this paper, we break down the self-Correction process into two core components: mistake finding and output correction. For mistake finding, we release BIG-Bench Mistake, a dataset of logical mistakes in Chain-of-Thought reasoning traces. For output