</>SkillRecallRECALL WHAT YOU KNOW
Prepare for an interviewExplore Library
AI Engineering / Working with LLMsEvaluation & Testing of LLM Outputs

15 items

1

Evaluating RAG Quality

Slides / Video
2

Evaluating RAG Quality

Quiz
3

Evaluating RAG Quality

Flashcard
4

Human Evaluation and Annotation

Flashcard
5

Inter-Annotator Agreement

Flashcard
6

Reference-Based vs Reference-Free

Flashcard
7

Why LLM Evaluation Is Hard

Flashcard
8

Rubric-Based Scoring

Flashcard
9

Pairwise vs Pointwise Judging

Flashcard
10

Assertion-Based Unit Testing of Outputs

Flashcard
11

LLM-as-a-Judge Evaluation

Flashcard
12

Semantic Similarity via Embeddings

Flashcard
13

Exact Match and String Matching

Flashcard
14

Building a Golden Evaluation Set

Flashcard
15

Overlap Metrics: BLEU, ROUGE, METEOR

Flashcard
Flashcard

Exact Match and String Matching

Exact match and string-based metrics check literal text equality, ideal for constrained outputs but brittle otherwise.

Question

When are exact-match and string-matching metrics appropriate?

Click to reveal answer