{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","description":"The assessment of large language models using measures, benchmarks, human judgments, or automated methods to characterize their performance and behavior.","display_name_alternatives":["large language model evaluation","evaluation of large language models","LLM assessment","large language model assessment","evaluating large language models","llm performance evaluation"],"ids":{"openalex":"https://openalex.org/keywords/llm-evaluation","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3479,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3479,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0832,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"works_count":4209,"cited_by_count":65527,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/llm-evaluation","updated_date":"2026-11-16T04:05:30","created_date":"2026-09-30T00:00:00"}
