{"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":"/code/preference-loss","entry":"preference_loss","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":9,"n_papers_ran":9,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":5,"n_samples_ran":5,"n_samples_fingerprinted":3,"n_places":9,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":3,"ran":2,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2508.08550","paper":"/paper/arxiv-2508-08550","title":"Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"CcQunResearch/SSPO","path":"SSPOTraining/Main/deepspeed_dpo.py","file_url":"https://github.com/CcQunResearch/SSPO/blob/HEAD/SSPOTraining/Main/deepspeed_dpo.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"318385490dec1ea1","mcp_get_code":{"code_sha256":"318385490dec1ea1"}},{"arxiv_id":"2409.17431","paper":"/paper/on-extending-direct-preference-optimization","title":"On Extending Direct Preference Optimization to Accommodate Ties","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-mitchell/direct-preference-optimization","path":"trainers.py","file_url":"https://github.com/eric-mitchell/direct-preference-optimization/blob/HEAD/trainers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c79211fc0225a27f","mcp_get_code":{"code_sha256":"c79211fc0225a27f"}},{"arxiv_id":"2407.10490","paper":"/paper/learning-dynamics-of-llm-finetuning","title":"Learning Dynamics of LLM Finetuning","date":"2024-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshua-ren/learning_dynamics_llm","path":"src/trainers.py","file_url":"https://github.com/joshua-ren/learning_dynamics_llm/blob/HEAD/src/trainers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c79211fc0225a27f","mcp_get_code":{"code_sha256":"c79211fc0225a27f"}},{"arxiv_id":"2407.07880","paper":"/paper/towards-robust-alignment-of-language-models","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junkangwu/dr_dpo","path":"trainers.py","file_url":"https://github.com/junkangwu/dr_dpo/blob/HEAD/trainers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c79211fc0225a27f","mcp_get_code":{"code_sha256":"c79211fc0225a27f"}},{"arxiv_id":"2405.20304","paper":"/paper/group-robust-preference-optimization-in","title":"Group Robust Preference Optimization in Reward-free RLHF","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rsshyam/Group-robust-preference-optimization","path":"src/loss_utils.py","file_url":"https://github.com/rsshyam/Group-robust-preference-optimization/blob/HEAD/src/loss_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"17df4b678a845f54","mcp_get_code":{"code_sha256":"17df4b678a845f54"}},{"arxiv_id":"2402.11907","paper":"/paper/direct-large-language-model-alignment-through","title":"Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"exlaw/dlma","path":"trainers.py","file_url":"https://github.com/exlaw/dlma/blob/HEAD/trainers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"838a07604a66c6c3","mcp_get_code":{"code_sha256":"838a07604a66c6c3"}},{"arxiv_id":"2402.10571","paper":"/paper/direct-preference-optimization-with-an-offset","title":"Direct Preference Optimization with an Offset","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rycolab/odpo","path":"trainers.py","file_url":"https://github.com/rycolab/odpo/blob/HEAD/trainers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"86c5aaf696fc2128","mcp_get_code":{"code_sha256":"86c5aaf696fc2128"}},{"arxiv_id":"2401.13275","paper":"/paper/can-ai-assistants-know-what-they-don-t-know","title":"Can AI Assistants Know What They Don't Know?","date":"2024-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmoss/say-i-dont-know","path":"src/dpo/trainers.py","file_url":"https://github.com/openmoss/say-i-dont-know/blob/HEAD/src/dpo/trainers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c79211fc0225a27f","mcp_get_code":{"code_sha256":"c79211fc0225a27f"}},{"arxiv_id":"2305.18290","paper":"/paper/direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icip-cas/Word-Deed-Consistency-Test","path":"dpo/trainers.py","file_url":"https://github.com/icip-cas/Word-Deed-Consistency-Test/blob/HEAD/dpo/trainers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c79211fc0225a27f","mcp_get_code":{"code_sha256":"c79211fc0225a27f"}}]}