{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6AR6RUUZYIFCBXBJECHFDZS3HB","short_pith_number":"pith:6AR6RUUZ","schema_version":"1.0","canonical_sha256":"f023e8d299c20a20dc29208e51e65b3847bb309eacc840dec01636572ee99791","source":{"kind":"arxiv","id":"2310.03668","version":5},"attestation_state":"computed","paper":{"title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eneko Agirre, German Rigau, Iker Garc\\'ia-Ferrero, Oier Lopez de Lacalle, Oscar Sainz, Rodrigo Agerri","submitted_at":"2023-10-05T16:43:13Z","abstract_excerpt":"Large Language Models (LLMs) combined with instruction tuning have made significant progress when generalizing to unseen tasks. However, they have been less successful in Information Extraction (IE), lagging behind task-specific models. Typically, IE tasks are characterized by complex annotation guidelines that describe the task and give examples to humans. Previous attempts to leverage such information have failed, even with the largest models, as they are not able to follow the guidelines out of the box. In this paper, we propose GoLLIE (Guideline-following Large Language Model for IE), a mo"},"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":"2310.03668","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T16:43:13Z","cross_cats_sorted":[],"title_canon_sha256":"1bff9dbf5c2268f7953de6ba17ce38a2c7f6c1a78bc202be007656ae9f5c6837","abstract_canon_sha256":"6b1b691e54da30da65b727e284bbad47fd94dd77658b3c46e5b0319ca9dc91e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:59.227688Z","signature_b64":"o8vWIZbVlnCrOtQXadwzQy7sKBG+Zq9MNKGKb+KwfI0XTSB7wDuc9D9eyNQTkXsDFpZD2LzkIUkhPZYSZQRWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f023e8d299c20a20dc29208e51e65b3847bb309eacc840dec01636572ee99791","last_reissued_at":"2026-07-05T07:52:59.227259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:59.227259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eneko Agirre, German Rigau, Iker Garc\\'ia-Ferrero, Oier Lopez de Lacalle, Oscar Sainz, Rodrigo Agerri","submitted_at":"2023-10-05T16:43:13Z","abstract_excerpt":"Large Language Models (LLMs) combined with instruction tuning have made significant progress when generalizing to unseen tasks. However, they have been less successful in Information Extraction (IE), lagging behind task-specific models. Typically, IE tasks are characterized by complex annotation guidelines that describe the task and give examples to humans. Previous attempts to leverage such information have failed, even with the largest models, as they are not able to follow the guidelines out of the box. In this paper, we propose GoLLIE (Guideline-following Large Language Model for IE), a mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03668","kind":"arxiv","version":5},"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/2310.03668/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":"2310.03668","created_at":"2026-07-05T07:52:59.227322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03668v5","created_at":"2026-07-05T07:52:59.227322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03668","created_at":"2026-07-05T07:52:59.227322+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AR6RUUZYIFC","created_at":"2026-07-05T07:52:59.227322+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AR6RUUZYIFCBXBJ","created_at":"2026-07-05T07:52:59.227322+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AR6RUUZ","created_at":"2026-07-05T07:52:59.227322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21890","citing_title":"Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03367","citing_title":"Automating Information Extraction and Retrieval for Industrial Spare Parts Pooling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30914","citing_title":"Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29407","citing_title":"LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14075","citing_title":"EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10633","citing_title":"ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB","json":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB.json","graph_json":"https://pith.science/api/pith-number/6AR6RUUZYIFCBXBJECHFDZS3HB/graph.json","events_json":"https://pith.science/api/pith-number/6AR6RUUZYIFCBXBJECHFDZS3HB/events.json","paper":"https://pith.science/paper/6AR6RUUZ"},"agent_actions":{"view_html":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB","download_json":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB.json","view_paper":"https://pith.science/paper/6AR6RUUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03668&json=true","fetch_graph":"https://pith.science/api/pith-number/6AR6RUUZYIFCBXBJECHFDZS3HB/graph.json","fetch_events":"https://pith.science/api/pith-number/6AR6RUUZYIFCBXBJECHFDZS3HB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB/action/storage_attestation","attest_author":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB/action/author_attestation","sign_citation":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB/action/citation_signature","submit_replication":"https://pith.science/pith/6AR6RUUZYIFCBXBJECHFDZS3HB/action/replication_record"}},"created_at":"2026-07-05T07:52:59.227322+00:00","updated_at":"2026-07-05T07:52:59.227322+00:00"}