{"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":"/paper/clarify-contrastive-preference-reinforcement","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","arxiv_id":"2506.00388","date":"2025-05-31","proceeding":null,"authors":["Ni Mu","Hao Hu","Xiao Hu","Yiqin Yang","Bo Xu","Qing-Shan Jia"],"abstract":"Preference-based reinforcement learning (PbRL) bypasses explicit reward engineering by inferring reward functions from human preference comparisons, enabling better alignment with human intentions. However, humans often struggle to label a clear preference between similar segments, reducing label efficiency and limiting PbRL's real-world applicability. To address this, we propose an offline PbRL method: Contrastive LeArning for ResolvIng Ambiguous Feedback (CLARIFY), which learns a trajectory embedding space that incorporates preference information, ensuring clearly distinguished segments are spaced apart, thus facilitating the selection of more unambiguous queries. Extensive experiments demonstrate that CLARIFY outperforms baselines in both non-ideal teachers and real human feedback settings. Our approach not only selects more distinguished queries but also learns meaningful trajectory embeddings.","url_abs":"https://arxiv.org/abs/2506.00388v2","url_pdf":"https://arxiv.org/pdf/2506.00388v2.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":"clarify-contrastive-preference-reinforcement","repo_url":"https://github.com/moonoutcloudback/clarify_pbrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.00388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00388"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","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/moonoutcloudback/clarify_pbrl","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"ran_fixture":2,"ran_violates":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"3d27511acaa0b08b","entry":"RewardModel","repo":"moonoutcloudback/clarify_pbrl","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d27511acaa0b08b"}},{"code_sha256_prefix":"21b25fb35ac731bf","entry":"compute_comparable_distribution_in_bins","repo":"moonoutcloudback/clarify_pbrl","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21b25fb35ac731bf"}},{"code_sha256_prefix":"2ed86e850091a5fc","entry":"compute_distribution","repo":"moonoutcloudback/clarify_pbrl","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ed86e850091a5fc"}},{"code_sha256_prefix":"a17d99b8eda680ff","entry":"gen_net","repo":"moonoutcloudback/clarify_pbrl","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a17d99b8eda680ff"}},{"code_sha256_prefix":"95e052b774320642","entry":"reject_sampling","repo":"moonoutcloudback/clarify_pbrl","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95e052b774320642"}},{"code_sha256_prefix":"b2f4aec40f7b3084","entry":"remove_outliers","repo":"moonoutcloudback/clarify_pbrl","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2f4aec40f7b3084"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}