즉, 모델이 사전 훈련이나 파인 튜닝 과정에서 학습한 정보나, 사용자로부터 입력받은 맥락과
일관되지 않은 내용을 생성하면 이를 환각이라고 정의합니다. 이러한 환각은 일반적으로 사실
에 근거하지 않은 텍스트로 나타납니다. 모델이 환각을 줄이려면 자신이 알지 못하는 사실이나
개념에 대해서는 모른다고 할 수 있어야 합니다.
다음은 환각의 전형적인 사례로, 누스리서치
NousResearch
의
Hermes
LLM
5
에 입력한 프롬프트와
그에 대한 응답입니다.
프롬프트:
2020년 올림픽에서 우간다 선수들이 획득한 메달 내역과 생년월일을 목록 형식으로 알려
주세요.
응답:
조슈아 체프테게이
Joshua ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.