{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/dpo/papers/5","list_of":"/method/dpo","method":"DPO","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":5,"pages_in_order":5,"rows_per_page":100,"rows":[401,409],"of":409,"counts":{"archive_papers_tagged":409,"with_a_code_link":184,"where_syntology_ran_a_sample":112,"not_listed_spam_title":0,"listed":409,"listed_where_code_ran":112,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":98,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":98,"listed_every_run_a_failure_of_syntologys_instrument":14,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/dpo","prev":"/method/dpo/papers/4","next":null,"papers":[{"paper":"/paper/a-general-theoretical-paradigm-to-understand","slug":"a-general-theoretical-paradigm-to-understand","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","date":"2023-10-18","arxiv_id":"2310.12036","n_code_links":1,"syntology":null},{"paper":"/paper/qilin-med-multi-stage-knowledge-injection","slug":"qilin-med-multi-stage-knowledge-injection","title":"Qilin-Med: Multi-stage Knowledge Injection Advanced Medical Large Language Model","date":"2023-10-13","arxiv_id":"2310.09089","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["williamliujl/Qilin-Med"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/improving-summarization-with-human-edits","slug":"improving-summarization-with-human-edits","title":"Improving Summarization with Human Edits","date":"2023-10-09","arxiv_id":"2310.05857","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["saiprabhakar/summarization_dpo_salt","seasonyao/learnfromhumanedit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/contrastive-post-training-large-language","slug":"contrastive-post-training-large-language","title":"Automatic Pair Construction for Contrastive Post-training","date":"2023-10-03","arxiv_id":"2310.02263","n_code_links":1,"syntology":null},{"paper":null,"slug":"parameter-efficient-tuning-helps-language","title":"Parameter-Efficient Tuning Helps Language Model Alignment","date":"2023-10-01","arxiv_id":"2310.00819","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-reverse-kl-generalizing-direct","slug":"beyond-reverse-kl-generalizing-direct","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","date":"2023-09-28","arxiv_id":"2309.16240","n_code_links":1,"syntology":{"ran":16,"of":17,"n_ran_checked":15,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"statistical-rejection-sampling-improves","title":"Statistical Rejection Sampling Improves Preference Optimization","date":"2023-09-13","arxiv_id":"2309.06657","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-large-language-models-better-reasoners","title":"Making Large Language Models Better Reasoners with Alignment","date":"2023-09-05","arxiv_id":"2309.02144","n_code_links":0,"syntology":null},{"paper":"/paper/direct-preference-optimization-your-language","slug":"direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","arxiv_id":"2305.18290","n_code_links":29,"syntology":{"ran":25,"of":31,"n_ran_checked":24,"n_instrument":1,"unverified":6,"pointer_only":2,"phrase":"25 ran (of which 1 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 0 violated, 24 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":null}}],"record_sha256":"2580bee8cbd09f9d33931440adf10316712c62962de42074af038284390fda6b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}