no code implementations • 19 Dec 2023 • Ziyi Chen, Jize Jiang, Daqian Zuo, Heyi Tao, Jun Yang, Yuxiang Wei
This results in high computational costs and limits the number of retrieved text, hindering accuracy.
no code implementations • 1 Mar 2023 • Adam Davies, Jize Jiang, ChengXiang Zhai
Our framework, CALM (Competence-based Analysis of Language Models), establishes the first quantitative measure of LLM competence, which we study by damaging models' internal representations of various linguistic properties in the course of performing various tasks using causal probing and evaluating models' alignment under these interventions with a given causal model.