{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ELIMZW6KFX2T4BHBHBUOJJR2NY","short_pith_number":"pith:ELIMZW6K","schema_version":"1.0","canonical_sha256":"22d0ccdbca2df53e04e13868e4a63a6e07f0930ebee6e9f9385a85086cc0eb2d","source":{"kind":"arxiv","id":"2407.07341","version":2},"attestation_state":"computed","paper":{"title":"A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gaurav Sahu, Issam H. Laradji, Olga Vechtomova","submitted_at":"2024-07-10T03:25:47Z","abstract_excerpt":"Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference time to generate summaries directly; however, such approaches often suffer from inconsistent LLM outputs and are difficult to adapt to domain-specific data in low-resource scenarios. In this work, we propose two novel methods to effectively utilize LLMs for low-resource text summarization: 1) MixSumm, an LLM-based data augmentation regime that synthesizes high-quality documents (short and long) for few-shot text summarization, and 2) PPSL, a prompt-based pseudo"},"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":"2407.07341","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T03:25:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5122ad9774d47eb49785f2b7779a6ca578cff23eb49aa2c787f04596800d26f","abstract_canon_sha256":"da60a092f9b37a9eb6519433cc620b69fa108e97989acb9b720af11ef6bf1bf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:39.076876Z","signature_b64":"EaZn8kl4vxABwGXfBST6jGlKUVqEsgCzrNQEfrVh3VOqpVh/3SJpbncHsB8u8xhw7ogeurPCISwaY/9i88ccAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22d0ccdbca2df53e04e13868e4a63a6e07f0930ebee6e9f9385a85086cc0eb2d","last_reissued_at":"2026-07-05T10:04:39.076414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:39.076414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gaurav Sahu, Issam H. Laradji, Olga Vechtomova","submitted_at":"2024-07-10T03:25:47Z","abstract_excerpt":"Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference time to generate summaries directly; however, such approaches often suffer from inconsistent LLM outputs and are difficult to adapt to domain-specific data in low-resource scenarios. In this work, we propose two novel methods to effectively utilize LLMs for low-resource text summarization: 1) MixSumm, an LLM-based data augmentation regime that synthesizes high-quality documents (short and long) for few-shot text summarization, and 2) PPSL, a prompt-based pseudo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07341","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/2407.07341/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":"2407.07341","created_at":"2026-07-05T10:04:39.076469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07341v2","created_at":"2026-07-05T10:04:39.076469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07341","created_at":"2026-07-05T10:04:39.076469+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELIMZW6KFX2T","created_at":"2026-07-05T10:04:39.076469+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELIMZW6KFX2T4BHB","created_at":"2026-07-05T10:04:39.076469+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELIMZW6K","created_at":"2026-07-05T10:04:39.076469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08218","citing_title":"PolicyStory: Leveraging Large Language Models to Generate Comprehensible Summaries of Policy-News in India","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY","json":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY.json","graph_json":"https://pith.science/api/pith-number/ELIMZW6KFX2T4BHBHBUOJJR2NY/graph.json","events_json":"https://pith.science/api/pith-number/ELIMZW6KFX2T4BHBHBUOJJR2NY/events.json","paper":"https://pith.science/paper/ELIMZW6K"},"agent_actions":{"view_html":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY","download_json":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY.json","view_paper":"https://pith.science/paper/ELIMZW6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07341&json=true","fetch_graph":"https://pith.science/api/pith-number/ELIMZW6KFX2T4BHBHBUOJJR2NY/graph.json","fetch_events":"https://pith.science/api/pith-number/ELIMZW6KFX2T4BHBHBUOJJR2NY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY/action/storage_attestation","attest_author":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY/action/author_attestation","sign_citation":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY/action/citation_signature","submit_replication":"https://pith.science/pith/ELIMZW6KFX2T4BHBHBUOJJR2NY/action/replication_record"}},"created_at":"2026-07-05T10:04:39.076469+00:00","updated_at":"2026-07-05T10:04:39.076469+00:00"}