liveBook · Manning

Evaluation dataset

As explained in LLM Evaluation and Alignment, The Foundational Ideas

A validation set is a dataset used to assess and tune a model or decision procedure during development.

An evaluation dataset provides examples and judgments for assessing a model or decision procedure. Depending on the task, it can contain expert-written reference answers, human labels, or query-document relevance judgments. section 1.1.2 section 6.2.4

For hallucination detection, build a validation set of 100–200 human-annotated responses, run the detector, and use its precision-recall curve to choose a threshold. Recalibrate periodically as models, users, or inputs change; the preferred threshold depends on the cost of false positives versus false negatives. section 5.4.3

For retrieval evaluation, assemble:

  • A corpus of documents. section 6.2.4
  • Queries, drawn from search logs or generated synthetically. section 6.2.4
  • Relevance judgments mapping queries to relevant documents. Human experts provide authoritative labels at higher cost; LLM judges and synthetic queries can scale labeling, but may introduce bias or mismatch real user queries. section 6.2.4
Figure 1.4 Reference-based evaluation workflow. Human experts create reference answers from a test set. The AI system generates candidate responses from the same inputs. The evaluator then compares each candidate's response with the corresponding reference response, producing scores.

Reference-based evaluation compares a system’s candidate response with a human-created reference for the same input. section 1.1.2

How LLM Evaluation and Alignment, The Foundational Ideas covers it

How deep it goes
Defines reference collections and retrieval labels, and gives detector-calibration steps with periodic recalibration.
Examples
Uses human reference answers for translation, annotated hallucination responses, and query-document relevance judgments.
What it assumes
Assumes task-specific reference answers or judgments, and defines retrieval labels as a corpus, queries, and relevance judgments.
What you can do after
Apply it by annotating detector responses, selecting thresholds from precision-recall curves, or labeling query-document relevance.
How it connects
Connects reference-based evaluation with hallucination detection, precision-recall curves, and retrieval evaluation.

Also explained in

Compare how 41 books explain evaluation dataset →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of LLM Evaluation and Alignment, The Foundational Ideas. The section links point to the parts of the book it draws on.