{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2V7JVHF6KINLUR2XRWPUXMEHX","short_pith_number":"pith:O2V7JVHF","schema_version":"1.0","canonical_sha256":"76abf4d4e5f290d5d23abc6cfa5d843dfd32e126c98bad0ff1f05e66fd2a48b9","source":{"kind":"arxiv","id":"2607.13315","version":1},"attestation_state":"computed","paper":{"title":"Meta-Learning Preferences for Multilingual LLM Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debmalya Mandal, Ilija Bogunovic, Jiaying Lin, Long Tran-Thanh, Nam Phuong Tran, Seongho Son","submitted_at":"2026-07-14T22:38:39Z","abstract_excerpt":"Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and me"},"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":"2607.13315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T22:38:39Z","cross_cats_sorted":[],"title_canon_sha256":"6aee69252e087a4c521b6cd23e20cce4d9b3fe9db1152e4bbde1a68be1a136a7","abstract_canon_sha256":"9a9b3e8560928efc58a5e37d812a03c63fdb27c82c710cda54268f866374a4c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:11.738964Z","signature_b64":"9l5kBBLX62UT5R00zk4kiiG0zCOGR1l2d+x3Hd47DF9+KpBJJ+72lapztoYBDYpDl8/X8Qzqtf/X99HNHCTGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76abf4d4e5f290d5d23abc6cfa5d843dfd32e126c98bad0ff1f05e66fd2a48b9","last_reissued_at":"2026-07-16T00:22:11.738147Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:11.738147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning Preferences for Multilingual LLM Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debmalya Mandal, Ilija Bogunovic, Jiaying Lin, Long Tran-Thanh, Nam Phuong Tran, Seongho Son","submitted_at":"2026-07-14T22:38:39Z","abstract_excerpt":"Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13315","kind":"arxiv","version":1},"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/2607.13315/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":"2607.13315","created_at":"2026-07-16T00:22:11.738567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13315v1","created_at":"2026-07-16T00:22:11.738567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13315","created_at":"2026-07-16T00:22:11.738567+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2V7JVHF6KIN","created_at":"2026-07-16T00:22:11.738567+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2V7JVHF6KINLUR2","created_at":"2026-07-16T00:22:11.738567+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2V7JVHF","created_at":"2026-07-16T00:22:11.738567+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/O2V7JVHF6KINLUR2XRWPUXMEHX","json":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX.json","graph_json":"https://pith.science/api/pith-number/O2V7JVHF6KINLUR2XRWPUXMEHX/graph.json","events_json":"https://pith.science/api/pith-number/O2V7JVHF6KINLUR2XRWPUXMEHX/events.json","paper":"https://pith.science/paper/O2V7JVHF"},"agent_actions":{"view_html":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX","download_json":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX.json","view_paper":"https://pith.science/paper/O2V7JVHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13315&json=true","fetch_graph":"https://pith.science/api/pith-number/O2V7JVHF6KINLUR2XRWPUXMEHX/graph.json","fetch_events":"https://pith.science/api/pith-number/O2V7JVHF6KINLUR2XRWPUXMEHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX/action/storage_attestation","attest_author":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX/action/author_attestation","sign_citation":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX/action/citation_signature","submit_replication":"https://pith.science/pith/O2V7JVHF6KINLUR2XRWPUXMEHX/action/replication_record"}},"created_at":"2026-07-16T00:22:11.738567+00:00","updated_at":"2026-07-16T00:22:11.738567+00:00"}