Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models

arXiv:2402.17124v1 Announce Type: new
Abstract: For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance. While it is now common sense that LLM performances are greatly impacted by prompts, the confidence calibration in prompting LLMs has yet to be thoroughly explored. In this paper, we explore how different prompting strategies influence LLM confidence calibration and how it could be improved. We conduct extensive experiments on six prompting methods in the question-answering context and we …

abstract arxiv common sense confidence cs.cl language language models large language large language models llm llms paper performance performances prompting prompting llms prompts sense trustworthy type