BriefGPT.xyz
Nov, 2023
Proto-lm: 基于原型网络的大型语言模型内置可解释性框架
Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models
HTML
PDF
Sean Xie, Soroush Vosoughi, Saeed Hassanpour
TL;DR
利用新型方法proto-lm，在维持性能竞争力的同时，使大语言模型具备了解释性，为实现可解释性的模型铺平了道路。
Abstract
large language models
(LLMs) have significantly advanced the field of Natural Language Processing (
nlp
), but their lack of
interpretability
→