{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LM3KQWEOPABNZ23C4QDEQDSPFP","short_pith_number":"pith:LM3KQWEO","schema_version":"1.0","canonical_sha256":"5b36a8588e7802dceb62e406480e4f2bd04628cf82f0c88069f2289c4c74d538","source":{"kind":"arxiv","id":"2406.06606","version":2},"attestation_state":"computed","paper":{"title":"Prototypical Reward Network for Data-Efficient RLHF","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyu Chen, Jinghan Zhang, Kunpeng Liu, Xinhao Zhang, Xiting Wang, Yiqiao Jin","submitted_at":"2024-06-06T15:23:30Z","abstract_excerpt":"The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues for LLMs and complex tasks. Our proposed framework Proto-RM leverages prototypical networks to enhance reward models under limited human feedback. By enabling stable and reliable structural learning from fewer samples, Proto-RM significantly enhances LLMs' adaptability and accuracy in interpreting human preferences. Extensive experiments on various datasets de"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.06606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T15:23:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"198d143955f71b6a76f513201135050a9e29c6b50b7dbd63c0f751e536ff28fc","abstract_canon_sha256":"c15e458849caeb990654a4c6219904c29090e15b38f640c8f6fcb55197535412"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:03.808230Z","signature_b64":"MyCVmY3mce+Nl/NWBYdOsvaNZg8ena9IFkJ3+lzh622neBolIrQNjrMRD0B2CVZd8zD3C5HaC75pQIzz+M29AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b36a8588e7802dceb62e406480e4f2bd04628cf82f0c88069f2289c4c74d538","last_reissued_at":"2026-07-05T08:41:03.807745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:03.807745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototypical Reward Network for Data-Efficient RLHF","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyu Chen, Jinghan Zhang, Kunpeng Liu, Xinhao Zhang, Xiting Wang, Yiqiao Jin","submitted_at":"2024-06-06T15:23:30Z","abstract_excerpt":"The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues for LLMs and complex tasks. Our proposed framework Proto-RM leverages prototypical networks to enhance reward models under limited human feedback. By enabling stable and reliable structural learning from fewer samples, Proto-RM significantly enhances LLMs' adaptability and accuracy in interpreting human preferences. Extensive experiments on various datasets de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06606","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.06606/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.06606","created_at":"2026-07-05T08:41:03.807808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06606v2","created_at":"2026-07-05T08:41:03.807808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06606","created_at":"2026-07-05T08:41:03.807808+00:00"},{"alias_kind":"pith_short_12","alias_value":"LM3KQWEOPABN","created_at":"2026-07-05T08:41:03.807808+00:00"},{"alias_kind":"pith_short_16","alias_value":"LM3KQWEOPABNZ23C","created_at":"2026-07-05T08:41:03.807808+00:00"},{"alias_kind":"pith_short_8","alias_value":"LM3KQWEO","created_at":"2026-07-05T08:41:03.807808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP","json":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP.json","graph_json":"https://pith.science/api/pith-number/LM3KQWEOPABNZ23C4QDEQDSPFP/graph.json","events_json":"https://pith.science/api/pith-number/LM3KQWEOPABNZ23C4QDEQDSPFP/events.json","paper":"https://pith.science/paper/LM3KQWEO"},"agent_actions":{"view_html":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP","download_json":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP.json","view_paper":"https://pith.science/paper/LM3KQWEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06606&json=true","fetch_graph":"https://pith.science/api/pith-number/LM3KQWEOPABNZ23C4QDEQDSPFP/graph.json","fetch_events":"https://pith.science/api/pith-number/LM3KQWEOPABNZ23C4QDEQDSPFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/action/storage_attestation","attest_author":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/action/author_attestation","sign_citation":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/action/citation_signature","submit_replication":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/action/replication_record"}},"created_at":"2026-07-05T08:41:03.807808+00:00","updated_at":"2026-07-05T08:41:03.807808+00:00"}