{"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/ran/2","list_of":"/method/dpo","method":"DPO","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,112],"of":112,"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/papers/ran/1","prev":"/method/dpo/papers/ran/1","next":null,"papers":[{"paper":"/paper/a-mechanistic-understanding-of-alignment","slug":"a-mechanistic-understanding-of-alignment","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","date":"2024-01-03","arxiv_id":"2401.01967","n_code_links":2,"syntology":{"ran":12,"of":14,"n_ran_checked":12,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ajyl/dpo_toxic"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/some-things-are-more-cringe-than-others","slug":"some-things-are-more-cringe-than-others","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss","date":"2023-12-27","arxiv_id":"2312.16682","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/what-makes-good-data-for-alignment-a","slug":"what-makes-good-data-for-alignment-a","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","date":"2023-12-25","arxiv_id":"2312.15685","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hkust-nlp/deita"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/policy-optimization-in-rlhf-the-impact-of-out","slug":"policy-optimization-in-rlhf-the-impact-of-out","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","date":"2023-12-17","arxiv_id":"2312.10584","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["liziniu/policy_optimization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ulma-unified-language-model-alignment-with","slug":"ulma-unified-language-model-alignment-with","title":"ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference","date":"2023-12-05","arxiv_id":"2312.02554","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["unified-language-model-alignment/src"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffusion-model-alignment-using-direct","slug":"diffusion-model-alignment-using-direct","title":"Diffusion Model Alignment Using Direct Preference Optimization","date":"2023-11-21","arxiv_id":"2311.12908","n_code_links":2,"syntology":{"ran":8,"of":10,"n_ran_checked":4,"n_instrument":4,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/direct-preference-optimization-for-neural","slug":"direct-preference-optimization-for-neural","title":"Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding","date":"2023-11-14","arxiv_id":"2311.08380","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bruceyg/dpo-mbr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/black-box-prompt-optimization-aligning-large","slug":"black-box-prompt-optimization-aligning-large","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","date":"2023-11-07","arxiv_id":"2311.04155","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thu-coai/bpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/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":"/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":"adc2eb6ab0bdc4f994342e49596a8974333fb818db767de498fb30661a231f68","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}