BriefGPT.xyz
Oct, 2023
了解LLMs不知道的内容：一种简单有效的自我检测方法
Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
HTML
PDF
Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Chong Meng...
TL;DR
提出了一种新颖的自我检测方法，通过扩展问题的文本表达并收集相应的答案，检测大型语言模型（LLMs）是否会产生虚假回答，证明了该方法在LLM效果上的有效性。
Abstract
large language models
(LLMs) have shown great potential in Natural Language Processing (NLP) tasks. However, recent literature reveals that LLMs generate
nonfactual responses
intermittently, which impedes the LLM
→