{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/prefscore-pairwise-preference-learning-for-1","title":"PrefScore: Pairwise Preference Learning for Reference-free Summarization Quality Assessment","arxiv_id":null,"date":"2022-10-01","proceeding":"COLING 2022 10","authors":["Ge Luo","Hebi Li","Youbiao He","Forrest Sheng Bao"],"abstract":"Evaluating machine-generated summaries without a human-written reference summary has been a need for a long time. Inspired by preference labeling in existing work of summarization evaluation, we propose to judge summary quality by learning the preference rank of summaries using the Bradley-Terry power ranking model from inferior summaries generated by corrupting base summaries. Extensive experiments on several datasets show that our weakly supervised scheme can produce scores highly correlated with human ratings.","url_abs":"https://aclanthology.org/2022.coling-1.515","url_pdf":"https://aclanthology.org/2022.coling-1.515.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"prefscore-pairwise-preference-learning-for-1","repo_url":"https://github.com/nkwbtb/prefscore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}