This story was originally published on HackerNoon at: https://hackernoon.com/llms-cannot-find-reasoning-errors-but-they-can-correct-them).
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](https://hackernoon.com/u/textmodels)). Learn more about this writer by checking [@textmodels's](https://hackernoon.com/about/textmodels)) about page,
and for more stories, please visit [hackernoon.com](https://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
