{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RVAPSIYQV5ZTQH4E3NBD4HAUW5","short_pith_number":"pith:RVAPSIYQ","schema_version":"1.0","canonical_sha256":"8d40f92310af73381f84db423e1c14b752cc333bb20033eea2a3f97c0b1914f7","source":{"kind":"arxiv","id":"2410.16168","version":2},"attestation_state":"computed","paper":{"title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashutosh Sathe, Divyanshu Aggarwal, Sunayana Sitaram","submitted_at":"2024-10-21T16:33:16Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate exceptional capabilities in a multitude of NLP tasks. However, the efficacy of such models to languages other than English is often limited. Prior works have shown that encoder-only models such as BERT or XLM-RoBERTa show impressive cross lingual transfer of their capabilities from English to other languages. In this work, we propose a pretraining strategy that uses active forgetting to achieve similar cross lingual transfer in decoder-only LLMs. We show that LLMs pretrained with active forgetting are highly effective when adapting to new and unseen lan"},"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":"2410.16168","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"3c315e1644d29c83f321e4d98231d51bab3d80d8597877ffe565abcace6f4c7e","abstract_canon_sha256":"5ce7c5d8c4bb37a9625466cba0f3a717c9dd9819ac91876b637df6c7ac2d36c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:24.418522Z","signature_b64":"erRJp6ML+M05CVZvexT5+F0Hk1wrcq3NGqqLOpPWMMnrDUGGiA2x8CY7D6PZjczDFUR8iAklf6I39nY2i0cVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d40f92310af73381f84db423e1c14b752cc333bb20033eea2a3f97c0b1914f7","last_reissued_at":"2026-07-05T11:06:24.418026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:24.418026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashutosh Sathe, Divyanshu Aggarwal, Sunayana Sitaram","submitted_at":"2024-10-21T16:33:16Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate exceptional capabilities in a multitude of NLP tasks. However, the efficacy of such models to languages other than English is often limited. Prior works have shown that encoder-only models such as BERT or XLM-RoBERTa show impressive cross lingual transfer of their capabilities from English to other languages. In this work, we propose a pretraining strategy that uses active forgetting to achieve similar cross lingual transfer in decoder-only LLMs. We show that LLMs pretrained with active forgetting are highly effective when adapting to new and unseen lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16168","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/2410.16168/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":"2410.16168","created_at":"2026-07-05T11:06:24.418083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16168v2","created_at":"2026-07-05T11:06:24.418083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16168","created_at":"2026-07-05T11:06:24.418083+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVAPSIYQV5ZT","created_at":"2026-07-05T11:06:24.418083+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVAPSIYQV5ZTQH4E","created_at":"2026-07-05T11:06:24.418083+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVAPSIYQ","created_at":"2026-07-05T11:06:24.418083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.21204","citing_title":"SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5","json":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5.json","graph_json":"https://pith.science/api/pith-number/RVAPSIYQV5ZTQH4E3NBD4HAUW5/graph.json","events_json":"https://pith.science/api/pith-number/RVAPSIYQV5ZTQH4E3NBD4HAUW5/events.json","paper":"https://pith.science/paper/RVAPSIYQ"},"agent_actions":{"view_html":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5","download_json":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5.json","view_paper":"https://pith.science/paper/RVAPSIYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16168&json=true","fetch_graph":"https://pith.science/api/pith-number/RVAPSIYQV5ZTQH4E3NBD4HAUW5/graph.json","fetch_events":"https://pith.science/api/pith-number/RVAPSIYQV5ZTQH4E3NBD4HAUW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/action/storage_attestation","attest_author":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/action/author_attestation","sign_citation":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/action/citation_signature","submit_replication":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/action/replication_record"}},"created_at":"2026-07-05T11:06:24.418083+00:00","updated_at":"2026-07-05T11:06:24.418083+00:00"}