{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T23:28:34Z","timestamp":1762298914449,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":3,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,29]]},"DOI":"10.1145\/3671127.3698711","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:30:41Z","timestamp":1730248241000},"page":"243-245","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Using DPO to align the building environment with personal preferences: A perspective from LLMs fine-tuning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5096-1619","authenticated-orcid":false,"given":"Zijie","family":"Chen","sequence":"first","affiliation":[{"name":"School of Design, Southern University of Science and Technology, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1381-8288","authenticated-orcid":false,"given":"Christiane M.","family":"Herr","sequence":"additional","affiliation":[{"name":"School of Design, Southern University of Science and Technology, Shenzhen, Guangdong, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Rafailov R. Sharma A. Mitchell E. Ermon S. Manning C.D. and Finn C. 2024. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. arXiv."},{"key":"e_1_3_2_1_2_1","volume-title":"Reinforcement Learning with Deep Deterministic Policy Gradient. 2021 International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) (May","author":"Tan H.","year":"2021","unstructured":"Tan, H. 2021. Reinforcement Learning with Deep Deterministic Policy Gradient. 2021 International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) (May 2021), 82--85."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/ina.13160"}],"event":{"name":"BuildSys '24: The 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","acronym":"BuildSys '24","location":"Hangzhou China"},"container-title":["Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3671127.3698711","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3671127.3698711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T23:24:18Z","timestamp":1762298658000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3671127.3698711"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"references-count":3,"alternative-id":["10.1145\/3671127.3698711","10.1145\/3671127"],"URL":"https:\/\/doi.org\/10.1145\/3671127.3698711","relation":{},"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"2024-10-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}