{"id":"https://openalex.org/keywords/language-model-training-data","display_name":"language model training data","description":"Language model training data is the text or other input material used to fit language models, with concerns including collection, quality, and rights.","display_name_alternatives":["training data for language models","language model training corpus","language model training corpora","LM training data"],"ids":{"openalex":"https://openalex.org/keywords/language-model-training-data","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5258,"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":0.5258,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1423,"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"}}],"works_count":314,"cited_by_count":2579,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/language-model-training-data","updated_date":"2026-11-22T04:06:09","created_date":"2026-09-30T00:00:00"}
