x

LESSWRONG
LW

Dewi Gould — LessWrong

Dewi Gould

Dewi Gould

Message

20

11mo

Dewi Gould hasn't written anything yet.

Dewi Gould

20

11mo

Dewi Gould has not written any posts yet.

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

This is a summary of our new paper. TL;DR: Existing faithfulness metrics are not suitable for evaluating frontier LLMs. We introduce a new metric based on whether a model's self-explanations help people predict its behavior on related inputs. We find self-explanations encode valuable information about a model decision-making process (though...