{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6UJCCHLVSW373SMPZIYQSTPMFN","short_pith_number":"pith:6UJCCHLV","schema_version":"1.0","canonical_sha256":"f512211d7595b7fdc98fca31094dec2b49e6762c018094204f48d0cbfbf790ea","source":{"kind":"arxiv","id":"2310.15326","version":1},"attestation_state":"computed","paper":{"title":"Specialist or Generalist? Instruction Tuning for Specific NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Chufan Shi, Deng Cai, Yixuan Su, Yujiu Yang","submitted_at":"2023-10-23T19:46:48Z","abstract_excerpt":"The potential of large language models (LLMs) to simultaneously perform a wide range of natural language processing (NLP) tasks has been the subject of extensive research. Although instruction tuning has proven to be a data-efficient method for transforming LLMs into such generalist models, their performance still lags behind specialist models trained exclusively for specific tasks. In this paper, we investigate whether incorporating broad-coverage generalist instruction tuning can contribute to building a specialist model. We hypothesize that its efficacy depends on task specificity and skill"},"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":"2310.15326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T19:46:48Z","cross_cats_sorted":[],"title_canon_sha256":"edc6c453d00307e56adb6dbd93794fdb32fdfa5969346f6a06956bef17bf6caa","abstract_canon_sha256":"81671bb26285418dc58fb963c297f10aad039dceabef8d7ce9d58c51caf5839d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:24.588794Z","signature_b64":"8A3dSmg1iyfv/MVrXuzFexZEEvlzo4hxFcb+1a8fVuG/Zr00bNDu4YjftBBs9VSUAIF8JvMLMcqQQ9PQ8oHfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f512211d7595b7fdc98fca31094dec2b49e6762c018094204f48d0cbfbf790ea","last_reissued_at":"2026-07-05T07:04:24.588387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:24.588387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Specialist or Generalist? Instruction Tuning for Specific NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Chufan Shi, Deng Cai, Yixuan Su, Yujiu Yang","submitted_at":"2023-10-23T19:46:48Z","abstract_excerpt":"The potential of large language models (LLMs) to simultaneously perform a wide range of natural language processing (NLP) tasks has been the subject of extensive research. Although instruction tuning has proven to be a data-efficient method for transforming LLMs into such generalist models, their performance still lags behind specialist models trained exclusively for specific tasks. In this paper, we investigate whether incorporating broad-coverage generalist instruction tuning can contribute to building a specialist model. We hypothesize that its efficacy depends on task specificity and skill"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15326","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/2310.15326/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":"2310.15326","created_at":"2026-07-05T07:04:24.588444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15326v1","created_at":"2026-07-05T07:04:24.588444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15326","created_at":"2026-07-05T07:04:24.588444+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UJCCHLVSW37","created_at":"2026-07-05T07:04:24.588444+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UJCCHLVSW373SMP","created_at":"2026-07-05T07:04:24.588444+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UJCCHLV","created_at":"2026-07-05T07:04:24.588444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22893","citing_title":"Agentic Enterprise: AI-Centric User to User-Centric AI","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN","json":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN.json","graph_json":"https://pith.science/api/pith-number/6UJCCHLVSW373SMPZIYQSTPMFN/graph.json","events_json":"https://pith.science/api/pith-number/6UJCCHLVSW373SMPZIYQSTPMFN/events.json","paper":"https://pith.science/paper/6UJCCHLV"},"agent_actions":{"view_html":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN","download_json":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN.json","view_paper":"https://pith.science/paper/6UJCCHLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15326&json=true","fetch_graph":"https://pith.science/api/pith-number/6UJCCHLVSW373SMPZIYQSTPMFN/graph.json","fetch_events":"https://pith.science/api/pith-number/6UJCCHLVSW373SMPZIYQSTPMFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN/action/storage_attestation","attest_author":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN/action/author_attestation","sign_citation":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN/action/citation_signature","submit_replication":"https://pith.science/pith/6UJCCHLVSW373SMPZIYQSTPMFN/action/replication_record"}},"created_at":"2026-07-05T07:04:24.588444+00:00","updated_at":"2026-07-05T07:04:24.588444+00:00"}