{"id":"https://openalex.org/keywords/dpo","display_name":"DPO","description":"Direct Preference Optimization is a method for aligning language models by training them on preference comparisons without a separate reward model.","display_name_alternatives":[],"ids":{"openalex":"https://openalex.org/keywords/dpo","wikidata":"https://www.wikidata.org/wiki/Q139833558"},"primary_topic":null,"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1848,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.082,"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":0.0725,"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":545,"cited_by_count":8281,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/dpo","updated_date":"2026-11-22T04:06:09","created_date":"2026-09-30T00:00:00"}
