{"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":"/paper/sample-efficient-reinforcement-learning-from","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","arxiv_id":"2312.00267","date":"2023-12-01","proceeding":null,"authors":["Viraj Mehta","Syrine Belakaria","Vikramjeet Das","Ojash Neopane","Yijia Dai","Ilija Bogunovic","Barbara Engelhardt","Stefano Ermon","Jeff Schneider","Willie Neiswanger"],"abstract":"Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, including in reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO). For many applications of preference alignment, the cost of acquiring human feedback can be substantial. In this work, we take advantage of the fact that one can often choose contexts at which to obtain human feedback to most efficiently identify a good policy, and formalize the setting as an active contextual dueling bandit problem. We propose an active exploration algorithm to efficiently select the data and provide theoretical proof that it has a polynomial worst-case regret bound. We extend the setting and methodology for practical use in preference alignment of large language models. We provide two extensions, an online and an offline approach. Our method outperforms the baselines with limited samples of human preferences on several language models and four real-world datasets including two new datasets that we contribute to the literature.","url_abs":"https://arxiv.org/abs/2312.00267v3","url_pdf":"https://arxiv.org/pdf/2312.00267v3.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":"sample-efficient-reinforcement-learning-from","repo_url":"https://github.com/belakaria/active-llm-alignment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.00267","atlas_url":"https://app.syntology.ai/?focus=2312.00267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00267"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.00267"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.00267"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.00267\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2312.00267"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2312.00267\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2312.00267"},"call":"get_concepts_for_paper(arxiv_id=\"2312.00267\")"}],"by_repo":[{"repo":"belakaria/active-llm-alignment","kind":"official","samples":7,"ran":6,"instrument":4,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2312.00267.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2312.00267.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/belakaria/active-llm-alignment","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":3,"ran":1,"unverified":1},"n_samples":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":7,"ran":6,"n_ran_checked":2,"n_instrument":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":1,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":6,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"c08d55f1fca01133","code_sha256_prefix":"c08d55f1fca01133","entry":"cat_pad_actions","repo":"belakaria/active-llm-alignment","repo_kind":"official","path":"data_selection.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/data_selection.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"action_list:list/1/Tensor, pad_token_id:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c08d55f1fca01133"}},{"code_sha256":"cb2b1a4a7f1ecabf","code_sha256_prefix":"cb2b1a4a7f1ecabf","entry":"dpo_loss","repo":"belakaria/active-llm-alignment","repo_kind":"official","path":"trainers.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/trainers.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"policy_chosen_logps:Tensor/1/float, policy_rejected_logps:Tensor/1/float, reference_chosen_logps:Tensor/1/float, reference_rejected_logps:Tensor/1/float, beta:float/0/float, reference_free:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/dpo-loss","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cb2b1a4a7f1ecabf"}},{"code_sha256":"12f6803880f9b17e","code_sha256_prefix":"12f6803880f9b17e","entry":"extract_anthropic_prompt","repo":"belakaria/active-llm-alignment","repo_kind":"official","path":"preference_datasets.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/preference_datasets.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"prompt_and_response:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/extract-anthropic-prompt","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from junkangwu/beta-DPO, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"12f6803880f9b17e"}},{"code_sha256":"f66e1f726f4fa9d6","code_sha256_prefix":"f66e1f726f4fa9d6","entry":"get_local_dir","repo":"belakaria/active-llm-alignment","repo_kind":"official","path":"utils.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prefixes_to_resolve:list/1/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-local-dir","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f66e1f726f4fa9d6"}},{"code_sha256":"96a26eed980b8eba","code_sha256_prefix":"96a26eed980b8eba","entry":"get_local_run_dir","repo":"belakaria/active-llm-alignment","repo_kind":"official","path":"utils.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"exp_name:str/0/str, local_dirs:list/1/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-local-run-dir","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"96a26eed980b8eba"}},{"code_sha256":"e7ce4c19888c6df6","code_sha256_prefix":"e7ce4c19888c6df6","entry":"get_remote_file","repo":"belakaria/active-llm-alignment","repo_kind":"official","path":"utils.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"remote_path:str/0/str, local_path:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T15:11:32.249708+00:00","code_page":"/code/get-remote-file","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"code_sha256":"4d36f6868ea2e4ab","code_sha256_prefix":"4d36f6868ea2e4ab","entry":"get_shp","repo":"belakaria/active-llm-alignment","repo_kind":"official","path":"preference_datasets.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/preference_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4d36f6868ea2e4ab"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ff77919f85852bff1ae808ba5cf7f50faab5349a773dca3c8d0c90d23070197e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}