{"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/kto-model-alignment-as-prospect-theoretic","title":"KTO: Model Alignment as Prospect Theoretic Optimization","arxiv_id":"2402.01306","date":"2024-02-02","proceeding":null,"authors":["Kawin Ethayarajh","Winnie Xu","Niklas Muennighoff","Dan Jurafsky","Douwe Kiela"],"abstract":"Kahneman & Tversky's $\\textit{prospect theory}$ tells us that humans perceive random variables in a biased but well-defined manner (1992); for example, humans are famously loss-averse. We show that objectives for aligning LLMs with human feedback implicitly incorporate many of these biases -- the success of these objectives (e.g., DPO) over cross-entropy minimization can partly be ascribed to them belonging to a family of loss functions that we call $\\textit{human-aware losses}$ (HALOs). However, the utility functions these methods attribute to humans still differ from those in the prospect theory literature. Using a Kahneman-Tversky model of human utility, we propose a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, as current methods do. We call this approach KTO, and it matches or exceeds the performance of preference-based methods at scales from 1B to 30B, despite only learning from a binary signal of whether an output is desirable. More broadly, our work suggests that there is no one HALO that is universally superior; the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.","url_abs":"https://arxiv.org/abs/2402.01306v4","url_pdf":"https://arxiv.org/pdf/2402.01306v4.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":"kto-model-alignment-as-prospect-theoretic","repo_url":"https://github.com/contextualai/halos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"kto-model-alignment-as-prospect-theoretic","repo_url":"https://github.com/openbmb/eurus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"kto-model-alignment-as-prospect-theoretic","repo_url":"https://github.com/reml-group/deliberation-on-priors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"kto-model-alignment-as-prospect-theoretic","repo_url":"https://github.com/tidedra/vl-rlhf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"kto-model-alignment-as-prospect-theoretic","repo_url":"https://github.com/uppaal/detox-edit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.01306","atlas_url":"https://app.syntology.ai/?focus=2402.01306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01306"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.01306"},"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":"2402.01306"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.01306\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2402.01306"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.01306\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.01306"},"call":"get_concepts_for_paper(arxiv_id=\"2402.01306\")"}],"by_repo":[{"repo":"contextualai/halos","kind":"official","samples":9,"ran":5,"instrument":2,"unverified":4},{"repo":"openbmb/eurus","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2404.02078"],"harvested_for_calls":[{"arxiv_id":"2404.02078","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.02078"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.02078\")"}]},{"repo":"reml-group/deliberation-on-priors","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2310.01061","2505.15210"],"harvested_for_calls":[{"arxiv_id":"2310.01061","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.01061"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.01061\")"},{"arxiv_id":"2505.15210","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.15210"},"call":"get_harvested_code_for_paper(arxiv_id=\"2505.15210\")"}]},{"repo":"tidedra/vl-rlhf","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2025.naacl-long.447"],"harvested_for_calls":[]},{"repo":"uppaal/detox-edit","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.13967"],"harvested_for_calls":[{"arxiv_id":"2405.13967","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.13967"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.13967\")"}]},{"repo":"jacklishufan/diffusion-kto","kind":"community","samples":2,"ran":0,"instrument":0,"unverified":2}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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/2402.01306.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/2402.01306.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/tidedra/vl-rlhf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/contextualai/halos","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openbmb/eurus","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/reml-group/deliberation-on-priors","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uppaal/detox-edit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":3,"unverified":6},"n_samples":11,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":6,"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":9,"ran":5,"n_ran_checked":3,"n_instrument":2,"repositories":1},"community":{"samples":2,"ran":0,"n_ran_checked":0,"n_instrument":0,"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":2,"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":0,"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":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","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":"65cbf1ea1a7a5e74","code_sha256_prefix":"65cbf1ea1a7a5e74","entry":"convert_to_binary_feedback","repo":"contextualai/halos","repo_kind":"official","path":"train/label.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/label.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":"samples:list/1/dict, threshold:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"65cbf1ea1a7a5e74"}},{"code_sha256":"9257a83ca14f9dd7","code_sha256_prefix":"9257a83ca14f9dd7","entry":"get_api_completion","repo":"contextualai/halos","repo_kind":"official","path":"train/utils.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"client:MockClient/0/?, system_prompt:str/0/str, user_prompt:str/0/str, model:str/0/str, temperature:float/0/float, max_retries:int/0/int, retry_delay:float/0/float","fixture_out_type":"coroutine","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9257a83ca14f9dd7"}},{"code_sha256":"1ed0ab0ac3d9655a","code_sha256_prefix":"1ed0ab0ac3d9655a","entry":"get_feedback","repo":"contextualai/halos","repo_kind":"official","path":"train/data.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"feedback_path:str/0/str, split:str/0/str","fixture_out_type":"Dataset","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-feedback","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1ed0ab0ac3d9655a"}},{"code_sha256":"38bf6f7230fcc687","code_sha256_prefix":"38bf6f7230fcc687","entry":"pad_to_length","repo":"contextualai/halos","repo_kind":"official","path":"train/utils.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"tensor:Tensor/2/float, length:int/0/int, pad_value:float/0/float, dim:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"38bf6f7230fcc687"},"code_page":"/code/pad-to-length","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"38bf6f7230fcc687"}},{"code_sha256":"500478230027c795","code_sha256_prefix":"500478230027c795","entry":"process_samples_with_api","repo":"contextualai/halos","repo_kind":"official","path":"train/label.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/label.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"samples:list/1/dict, client:callable/0/?, system_prompt:str/0/str, label_prompt:str/0/str, model:str/0/str, batch_size:int/0/int","fixture_out_type":"coroutine","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"500478230027c795"}},{"code_sha256":"c54cf81b72eecb67","code_sha256_prefix":"c54cf81b72eecb67","entry":"get_alpacaeval","repo":"contextualai/halos","repo_kind":"official","path":"train/data.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/data.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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c54cf81b72eecb67"}},{"code_sha256":"124288769111d62f","code_sha256_prefix":"124288769111d62f","entry":"get_base_model_state_dict_from_peft","repo":"contextualai/halos","repo_kind":"official","path":"train/utils.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/utils.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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"124288769111d62f"}},{"code_sha256":"238fc17a8a274cea","code_sha256_prefix":"238fc17a8a274cea","entry":"get_sampled_data","repo":"contextualai/halos","repo_kind":"official","path":"train/data.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/data.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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"238fc17a8a274cea"}},{"code_sha256":"20f9d022f6c9a501","code_sha256_prefix":"20f9d022f6c9a501","entry":"parse_args","repo":"jacklishufan/diffusion-kto","repo_kind":"community","path":"train_kto_sd_v1.5.py","file_url":"https://github.com/jacklishufan/diffusion-kto/blob/HEAD/train_kto_sd_v1.5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/parse-args","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jacklishufan/diffusion-kto when it was checked","mcp_get_code":{"code_sha256":"20f9d022f6c9a501"}},{"code_sha256":"9bf64659a7cf741d","code_sha256_prefix":"9bf64659a7cf741d","entry":"process_batch_with_reward_model","repo":"contextualai/halos","repo_kind":"official","path":"train/label.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/label.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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9bf64659a7cf741d"}},{"code_sha256":"28cae3111ef3900a","code_sha256_prefix":"28cae3111ef3900a","entry":"tokenize_captions","repo":"jacklishufan/diffusion-kto","repo_kind":"community","path":"train_kto_sd_v1.5.py","file_url":"https://github.com/jacklishufan/diffusion-kto/blob/HEAD/train_kto_sd_v1.5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/tokenize-captions","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jacklishufan/diffusion-kto when it was checked","mcp_get_code":{"code_sha256":"28cae3111ef3900a"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5d80e07aae5b42798ac911c11c1de7db3ca55d6560bda020038be260ecda1e02","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}