{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MYGTVZRJRGFVJ2DT5JASEYIBOX","short_pith_number":"pith:MYGTVZRJ","schema_version":"1.0","canonical_sha256":"660d3ae629898b54e873ea4122610175cfb8464e8e7ee3dae94d5f24d0f0c666","source":{"kind":"arxiv","id":"2310.05092","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changlong Yu, Huan Zhao, Jun Gao, Ruifeng Xu, Wei Wang, Yice Zhang","submitted_at":"2023-10-08T09:41:18Z","abstract_excerpt":"Information Extraction (IE) is an essential task in Natural Language Processing. Traditional methods have relied on coarse-grained extraction with simple instructions. However, with the emergence of Large Language Models (LLMs), there is a need to adapt IE techniques to leverage the capabilities of these models. This paper introduces a fine-grained IE benchmark dataset tailored for LLMs, employing augmented instructions for each information type, which includes task descriptions, extraction rules, output formats, and examples. Through extensive evaluations, we observe that encoder-decoder mode"},"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":"2310.05092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T09:41:18Z","cross_cats_sorted":[],"title_canon_sha256":"73737b6df4ab37d71f1e0697f33f64c35628dbc380c01c6abfc5153a1c809f2a","abstract_canon_sha256":"ff34b77efe2e9220db909ac1c9e8d31fac0bfe39d142ccf7d226871b22241f79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:26.546846Z","signature_b64":"sFDbXjcywA2UyHTEONC0VZ5At5WzrSdfZ2bBnjxRKeaiJ5o8n6zOeRWTVuSllFYdXjT0pUyeIpPwDra/XrNGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"660d3ae629898b54e873ea4122610175cfb8464e8e7ee3dae94d5f24d0f0c666","last_reissued_at":"2026-07-05T06:58:26.546422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:26.546422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changlong Yu, Huan Zhao, Jun Gao, Ruifeng Xu, Wei Wang, Yice Zhang","submitted_at":"2023-10-08T09:41:18Z","abstract_excerpt":"Information Extraction (IE) is an essential task in Natural Language Processing. Traditional methods have relied on coarse-grained extraction with simple instructions. However, with the emergence of Large Language Models (LLMs), there is a need to adapt IE techniques to leverage the capabilities of these models. This paper introduces a fine-grained IE benchmark dataset tailored for LLMs, employing augmented instructions for each information type, which includes task descriptions, extraction rules, output formats, and examples. Through extensive evaluations, we observe that encoder-decoder mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05092","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/2310.05092/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":"2310.05092","created_at":"2026-07-05T06:58:26.546484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05092v1","created_at":"2026-07-05T06:58:26.546484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05092","created_at":"2026-07-05T06:58:26.546484+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYGTVZRJRGFV","created_at":"2026-07-05T06:58:26.546484+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYGTVZRJRGFVJ2DT","created_at":"2026-07-05T06:58:26.546484+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYGTVZRJ","created_at":"2026-07-05T06:58:26.546484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.14075","citing_title":"EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX","json":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX.json","graph_json":"https://pith.science/api/pith-number/MYGTVZRJRGFVJ2DT5JASEYIBOX/graph.json","events_json":"https://pith.science/api/pith-number/MYGTVZRJRGFVJ2DT5JASEYIBOX/events.json","paper":"https://pith.science/paper/MYGTVZRJ"},"agent_actions":{"view_html":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX","download_json":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX.json","view_paper":"https://pith.science/paper/MYGTVZRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05092&json=true","fetch_graph":"https://pith.science/api/pith-number/MYGTVZRJRGFVJ2DT5JASEYIBOX/graph.json","fetch_events":"https://pith.science/api/pith-number/MYGTVZRJRGFVJ2DT5JASEYIBOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX/action/storage_attestation","attest_author":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX/action/author_attestation","sign_citation":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX/action/citation_signature","submit_replication":"https://pith.science/pith/MYGTVZRJRGFVJ2DT5JASEYIBOX/action/replication_record"}},"created_at":"2026-07-05T06:58:26.546484+00:00","updated_at":"2026-07-05T06:58:26.546484+00:00"}