{"id":"https://openalex.org/keywords/direct-preference-optimization","display_name":"direct preference optimization","description":"A machine-learning method for aligning language models with human preferences by training directly on preferred and dispreferred outputs, without a separate reward model.","display_name_alternatives":["direct preference optimisation","DPO"],"ids":{"openalex":"https://openalex.org/keywords/direct-preference-optimization","wikidata":"https://www.wikidata.org/wiki/Q139833558"},"primary_topic":null,"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1888,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0994,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.0787,"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":1709,"cited_by_count":39329,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/direct-preference-optimization","updated_date":"2026-11-17T04:05:58","created_date":"2026-09-30T00:00:00"}
