The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models

arXiv:2404.03189v1 Announce Type: new
Abstract: In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural language explanations or reasoning traces that sound plausible and receive high ratings from human annotators. However, it is unclear to what extent these explanations are faithful, i.e., truly capture the factors responsible for the model's predictions. In this work, we introduce Correlational Explanatory Faithfulness (CEF), a metric that can be …

abstract advanced advanced ai ai systems arxiv cs.ai cs.cl decision free language language models large language large language models llms making matter natural natural language process ratings reasoning sound systems text traces type