{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WSGZ2G2GOYK7VL7L3H4XMSLSGD","short_pith_number":"pith:WSGZ2G2G","schema_version":"1.0","canonical_sha256":"b48d9d1b467615faafebd9f976497230ed2ae2d6ca9a4ba7b82d30b1ae31107c","source":{"kind":"arxiv","id":"2407.10582","version":1},"attestation_state":"computed","paper":{"title":"Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sunil Agrawal, Barah Fazili, Preethi Jyothi","submitted_at":"2024-07-15T10:00:22Z","abstract_excerpt":"Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingual transfer for low-resource target languages. Given task-specific data in a source language and a teacher model trained on this data, we propose using this teacher to label LLM generations and employ a set of simple data selection strategies that use the teacher's label probabilities. Our data selection strategies help us identify a representative subset of diverse generations that help boost zero-shot accuracies wh"},"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":"2407.10582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T10:00:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b2c522003af040124a657ac95156b123cc29d2b3b1f374212331d604419181b","abstract_canon_sha256":"f46f11953d9eab9f626cd9966622f6fb94ebae7b6e9169dabb542471ca9571aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:01.372348Z","signature_b64":"Bj5AWxol6u9YCr6/1E6SvFrSMLPk2f17rDow/IkoQPhWyHn93LddWdrqzFKIh9WYgDEy1CUwhhYyDrN5gehbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b48d9d1b467615faafebd9f976497230ed2ae2d6ca9a4ba7b82d30b1ae31107c","last_reissued_at":"2026-07-05T08:44:01.371935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:01.371935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sunil Agrawal, Barah Fazili, Preethi Jyothi","submitted_at":"2024-07-15T10:00:22Z","abstract_excerpt":"Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingual transfer for low-resource target languages. Given task-specific data in a source language and a teacher model trained on this data, we propose using this teacher to label LLM generations and employ a set of simple data selection strategies that use the teacher's label probabilities. Our data selection strategies help us identify a representative subset of diverse generations that help boost zero-shot accuracies wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10582","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/2407.10582/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":"2407.10582","created_at":"2026-07-05T08:44:01.371998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10582v1","created_at":"2026-07-05T08:44:01.371998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10582","created_at":"2026-07-05T08:44:01.371998+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSGZ2G2GOYK7","created_at":"2026-07-05T08:44:01.371998+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSGZ2G2GOYK7VL7L","created_at":"2026-07-05T08:44:01.371998+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSGZ2G2G","created_at":"2026-07-05T08:44:01.371998+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/WSGZ2G2GOYK7VL7L3H4XMSLSGD","json":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD.json","graph_json":"https://pith.science/api/pith-number/WSGZ2G2GOYK7VL7L3H4XMSLSGD/graph.json","events_json":"https://pith.science/api/pith-number/WSGZ2G2GOYK7VL7L3H4XMSLSGD/events.json","paper":"https://pith.science/paper/WSGZ2G2G"},"agent_actions":{"view_html":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD","download_json":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD.json","view_paper":"https://pith.science/paper/WSGZ2G2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10582&json=true","fetch_graph":"https://pith.science/api/pith-number/WSGZ2G2GOYK7VL7L3H4XMSLSGD/graph.json","fetch_events":"https://pith.science/api/pith-number/WSGZ2G2GOYK7VL7L3H4XMSLSGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD/action/storage_attestation","attest_author":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD/action/author_attestation","sign_citation":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD/action/citation_signature","submit_replication":"https://pith.science/pith/WSGZ2G2GOYK7VL7L3H4XMSLSGD/action/replication_record"}},"created_at":"2026-07-05T08:44:01.371998+00:00","updated_at":"2026-07-05T08:44:01.371998+00:00"}