상황별 AI 엔터프라이즈 RAG 퀴즈

퀴즈를 풀면 정답과 설명이 나타납니다.

1. RAG라는 약어는 무엇을 의미합니까?
   • 검색 증강 생성
   • 재귀 알고리즘 생성
   • 순위 답변 접지
   • 실시간 API 게이트웨이
2. What connection does Contextual AI co-founder Douwe Kiela have to the original 2020 RAG paper?
   • He was the paper’s only author
   • He is one of the paper’s co-authors
   • He founded the research lab that published the paper
   • He led the company that acquired the paper’s dataset
3. What is the stated training goal of Contextual AI’s grounded language model?
   • Guarantee that every answer is factually correct
   • Replace document retrieval with the model’s internal memory
   • Base answers on retrieved passages and express uncertainty when evidence is missing
   • Satisfy every regulatory requirement by adding a citation
4. RAG 파이프라인에서 순위 재지정 단계는 무엇을 합니까?
   • 중복 문서를 영구적으로 삭제합니다.
   • 소스 데이터를 암호화합니다.
   • 기본 모델을 처음부터 학습합니다.
   • 검색된 후보를 생성 전 관련성에 따라 재정렬합니다.
5. 벡터 데이터베이스에 연결된 일반 챗봇에 비해 상황별 AI가 주장하는 이점은 무엇입니까?
   • 모든 구성 요소는 하나의 최적화된 시스템으로 공동 조정됩니다.
   • 서류가 전혀 필요하지 않습니다
   • 컴퓨터 없이도 완전히 실행됩니다.
   • 공개 웹 데이터에서만 작동합니다.
6. How can citations help a reviewer assess an enterprise RAG answer?
   • They automatically satisfy regulatory compliance
   • They let the reviewer trace claims to retrieved source passages
   • They prove every model output is correct
   • They eliminate the need to check data access and retention
7. What document feature does Contextual AI's parser aim to preserve for enterprise RAG?
   • Only the file's creation timestamp
   • The model's private training weights
   • Document structure such as hierarchy and tables
   • A chat history unrelated to the source document
8. Which evaluation component does Contextual AI list alongside parsing, reranking, and generation?
   • A GPU scheduler for model training
   • An image upsampler for document figures
   • A biometric login service for analysts
   • LMUnit for preference, direct-scoring, and natural-language unit-test evaluation