{"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/log-init","entry":"log_init","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":10,"n_papers_ran":0,"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":1,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":1},"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":"2602.01685","paper":"/paper/arxiv-2602-01685","title":"Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"aailab-kaist/WPR","path":"applications/DeepSpeed-Chat/dschat/rlhf/rlhf_wpr_engine.py","file_url":"https://github.com/aailab-kaist/WPR/blob/HEAD/applications/DeepSpeed-Chat/dschat/rlhf/rlhf_wpr_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2410.16843","paper":"/paper/trustworthy-alignment-of-retrieval-augmented","title":"Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zmzhang2000/trustworthy-alignment","path":"dschat/rlhf/rlhf_engine.py","file_url":"https://github.com/zmzhang2000/trustworthy-alignment/blob/HEAD/dschat/rlhf/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2407.16574","paper":"/paper/tlcr-token-level-continuous-reward-for-fine","title":"TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"esyoon7/rlhf-tlcr","path":"step3_rlhf_finetuning_tlcr/rlhf_engine.py","file_url":"https://github.com/esyoon7/rlhf-tlcr/blob/HEAD/step3_rlhf_finetuning_tlcr/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2405.16455","paper":"/paper/on-the-algorithmic-bias-of-aligning-large","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JiancongXiao/PM_RLHF","path":"dschat/rlhf/rlhf_engine.py","file_url":"https://github.com/JiancongXiao/PM_RLHF/blob/HEAD/dschat/rlhf/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2404.17287","paper":"/paper/when-to-trust-llms-aligning-confidence-with","title":"When to Trust LLMs: Aligning Confidence with Response Quality","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taoshuchang/conqord","path":"step3_RL_finetune_LLM/rlhf_engine.py","file_url":"https://github.com/taoshuchang/conqord/blob/HEAD/step3_RL_finetune_LLM/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2402.05808","paper":"/paper/training-large-language-models-for-reasoning","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"woooodyy/llm-reverse-curriculum-rl","path":"R3_others/dschat/rlhf/rlhf_engine.py","file_url":"https://github.com/woooodyy/llm-reverse-curriculum-rl/blob/HEAD/R3_others/dschat/rlhf/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"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/deepspeed-chat-ppo/rlhf_engine.py","file_url":"https://github.com/openmoss/say-i-dont-know/blob/HEAD/src/deepspeed-chat-ppo/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2310.10505","paper":"/paper/remax-a-simple-effective-and-efficient-method","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liziniu/ReMax","path":"step3_rlhf_finetuning/rlhf_engine.py","file_url":"https://github.com/liziniu/ReMax/blob/HEAD/step3_rlhf_finetuning/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2308.02223","paper":"/paper/esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangclnlp/DeepSpeed-Chat-Extension","path":"rlhf_llama/deepspeed_chat/training/step3_rlhf_finetuning/rlhf_engine.py","file_url":"https://github.com/wangclnlp/DeepSpeed-Chat-Extension/blob/HEAD/rlhf_llama/deepspeed_chat/training/step3_rlhf_finetuning/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}},{"arxiv_id":"2024.naacl-long.326","paper":null,"title":"arXiv:2024.naacl-long.326","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LanXiu0523/RLHF_instructGPT","path":"applications/train/rlhf_engine.py","file_url":"https://github.com/LanXiu0523/RLHF_instructGPT/blob/HEAD/applications/train/rlhf_engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"429d42a3bf925da5","mcp_get_code":{"code_sha256":"429d42a3bf925da5"}}]}