April 2026
Intermediate
348 pages
8h 22m
Korean
Content preview from 그림으로 배우는 생성형 AI
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,
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.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.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.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.
2915
장 생성형 AI 애플리케이션의 아키텍처
할 수 있습니다
.
어댑터 조정으로 만든 모델을 사용할
때와 비슷한 방식입니다
.
5.6.3 RLHF
지금까지 어댑터 조정과 증류라는 두 가지 형태의 미
세조정을 살펴보았습니다
.
이제 미세조정의 셋째 형
태인
,
인간의 피드백에 기반해서 모델을 개선하는
RLHF
를 알아보겠습니다
(
그림
5
-
25
).
RLHF를 언제 어떻게 적용해야 할까?
RLHF
는 사용자 피드백을 기반으로 모델을 개선하는
방법으로
,
단 하나의 정답이 없는 활용 사례에서 자
주 쓰입니다
.
생성형
AI
애플리케이션을 개발할 때
RLHF
를 어떤 식으로 적용하면 좋을까요
?
다음은 몇
가지 아이디어입니다
.
프로덕션 단계
한 가지 접근법은 모델을 프로덕션에 배포하는 과
정에서 명시적으로 인간 선호도 데이터셋을 생성하
는 것입니다
.
후보 모델을 사용해서 출력 쌍을 생성
한 다음
,
출력 쌍을 인간 테스터 그룹에게 보내 점
수를 매기도록 합니다
.
이러한 접근법의 문제점은
테스터들이 실제 최종 사용자를 잘 대표하지 못할
수 있다는 것입니다
.
명시적 피드백
모델을 배포한 후에도
A
/
B
테스팅 프레임워크를
사용해서 선호도 데이터셋을 계속 강화할 수 있습
니다
.
생성된 텍스트
,
답변 또는 이미지에 대해 좋
아요
/
싫어요 형태로 인간 피드백을 요청해서 데이
터를 수집하고
,
모든 프롬프트
,
답변 ...
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.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
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.
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.
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.
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.