Start natural voice conversations anytime with GPT-LiveTrack the latest safety rules for bigger modelsChatGPT Voice feels more natural in live conversationTranslate naturally during calls, meetings, and travelEasily automate multi-step daily tasks at lower costMake Claude easier to deploy through AWSClaude Fable 5 is usable again after the pauseKeep research tools and analysis in one placeKeep research tools in one place and move fasterDelegate more everyday coding work to ClaudeMeasure how well AI agents handle ambiguous biology research judgmentsClaude Sonnet 5 is built for heavier coding and work tasksHP partnership makes enterprise rollout easierTag Claude in Slack to delegate tasks with your whole teamHand Slack tasks to Claude more easilyConfidential AI gets stronger for sensitive workloadsHelps defenders validate and fix vulnerabilitiesGemini API key management is moving to safer auth keysGoogle Home Speaker makes home control feel naturalClaude expands more easily into Korean businesses and researchStart natural voice conversations anytime with GPT-LiveTrack the latest safety rules for bigger modelsChatGPT Voice feels more natural in live conversationTranslate naturally during calls, meetings, and travelEasily automate multi-step daily tasks at lower costMake Claude easier to deploy through AWSClaude Fable 5 is usable again after the pauseKeep research tools and analysis in one placeKeep research tools in one place and move fasterDelegate more everyday coding work to ClaudeMeasure how well AI agents handle ambiguous biology research judgmentsClaude Sonnet 5 is built for heavier coding and work tasksHP partnership makes enterprise rollout easierTag Claude in Slack to delegate tasks with your whole teamHand Slack tasks to Claude more easilyConfidential AI gets stronger for sensitive workloadsHelps defenders validate and fix vulnerabilitiesGemini API key management is moving to safer auth keysGoogle Home Speaker makes home control feel naturalClaude expands more easily into Korean businesses and research
Official sources only. Rumors, leaks, and get-rich schemes are excluded.
← Back to glossary
GlossaryAI term

Automated Evaluation

自動評価

Definition

Automated evaluation is a method that measures output quality mechanically using rules or other models to speed up iteration cycles. It scales well but must be checked against human judgment to avoid drift.

Having humans read hundreds of outputs every time a model is improved is simply not realistic. Evaluation cannot keep pace with the speed of development. Automated evaluation is an assessment method that programmatically scores AI output quality using rule-based or model-based approaches.

Rule-Based Automated Evaluation

The simplest form of automated evaluation uses clear rules for judgment. For example, code generation uses test case pass rates, translation uses BLEU scores (measuring agreement with reference translations), and summarization uses ROUGE scores (measuring overlap with reference summaries). These metrics have been used for years. They offer the advantage of being fast to compute and highly reproducible, but they have limitations for tasks where there is no single correct answer. The quality of natural conversation or creative writing cannot be measured by simple string comparison.

LLM-as-Judge

An approach that has rapidly gained popularity in recent years is "LLM-as-Judge," which uses an LLM itself as the evaluator. High-performance models such as GPT-4 or Claude 3.5 are given evaluation criteria (rubrics) and asked to score the outputs of other models. This method is used in well-known benchmarks such as MT-Bench and AlpacaEval.

The advantage of LLM-as-Judge is that it can make flexible judgments close to human evaluation while being able to evaluate thousands of outputs in minutes. Because rapid feedback can be obtained with every prompt change or model update, the iteration speed of development improves dramatically.

The Need for Calibration

To trust automated evaluation, calibration that verifies correlation with human evaluation is essential. LLM-as-Judge has known biases: it tends to rate longer answers higher (verbosity bias), prefer the answer presented first (position bias), and favor outputs from the same model family (self-bias).

To correct these biases, countermeasures include randomizing the order of evaluation targets, comparing results using multiple evaluation models, and periodically cross-checking with human evaluation to verify score alignment.

Practical Usage

The current best practice is a two-tier approach: using automated evaluation for day-to-day development cycles and supplementing with human evaluation for important release decisions. Automated evaluation excels at quickly detecting obvious quality degradation, while human evaluation excels at accurately judging subtle quality differences. Combining both enables achieving both development speed and evaluation accuracy.

h
hayami

Stay on top of OpenAI, Google & Anthropic updates. An AI digest for business professionals.

Source Policy

We use only official sources. Each article links to the original announcement so you can verify it yourself.

© 2026 hayami. All rights reserved.