DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging

Lin T.H.HUNG-YI LEE2025-03-202025-03-202024-01-01979-889176164-3https://www.scopus.com/record/display.uri?eid=2-s2.0-85215220936&origin=resultslisthttps://scholars.lib.ntu.edu.tw/handle/123456789/725912falseDogeRM: Equipping Reward Models with Domain Knowledge through Model Mergingconference paper2-s2.0-85215220936