{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZVR33JR5ZZL4YO3U7IL46NTLC5","short_pith_number":"pith:ZVR33JR5","schema_version":"1.0","canonical_sha256":"cd63bda63dce57cc3b74fa17cf366b174cded308e296ac16d425a8395dd251f0","source":{"kind":"arxiv","id":"2405.04960","version":2},"attestation_state":"computed","paper":{"title":"P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deqing Yang, Guochao Jiang, Yuchen Shi, Zepeng Ding","submitted_at":"2024-05-08T11:01:21Z","abstract_excerpt":"In recent years, the rise of large language models (LLMs) has made it possible to directly achieve named entity recognition (NER) without any demonstration samples or only using a few samples through in-context learning (ICL). However, standard ICL only helps LLMs understand task instructions, format and input-label mapping, but neglects the particularity of the NER task itself. In this paper, we propose a new prompting framework P-ICL to better achieve NER with LLMs, in which some point entities are leveraged as the auxiliary information to recognize each entity type. With such significant in"},"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":"2405.04960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T11:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"2a173e2f5a099e9d6686ff9c3d34ef0d30b99fe9c277338d7ca35d4ff0673cd6","abstract_canon_sha256":"6d76f8ca8dfc95727fe0dc522d7c2423a412ad34612a3839a95c8b0bd557bb99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:40.431907Z","signature_b64":"q0NCSsGyPAVqmqzvcX4a2B3dQpfarJ/q001UlTRn5W0mkp37kZkug8Y+UEO8GZbQn9xAo2NKwpqV5q0Z6ZzWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd63bda63dce57cc3b74fa17cf366b174cded308e296ac16d425a8395dd251f0","last_reissued_at":"2026-07-05T08:32:40.431344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:40.431344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deqing Yang, Guochao Jiang, Yuchen Shi, Zepeng Ding","submitted_at":"2024-05-08T11:01:21Z","abstract_excerpt":"In recent years, the rise of large language models (LLMs) has made it possible to directly achieve named entity recognition (NER) without any demonstration samples or only using a few samples through in-context learning (ICL). However, standard ICL only helps LLMs understand task instructions, format and input-label mapping, but neglects the particularity of the NER task itself. In this paper, we propose a new prompting framework P-ICL to better achieve NER with LLMs, in which some point entities are leveraged as the auxiliary information to recognize each entity type. With such significant in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04960","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/2405.04960/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":"2405.04960","created_at":"2026-07-05T08:32:40.431413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04960v2","created_at":"2026-07-05T08:32:40.431413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04960","created_at":"2026-07-05T08:32:40.431413+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVR33JR5ZZL4","created_at":"2026-07-05T08:32:40.431413+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVR33JR5ZZL4YO3U","created_at":"2026-07-05T08:32:40.431413+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVR33JR5","created_at":"2026-07-05T08:32:40.431413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19128","citing_title":"RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5","json":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5.json","graph_json":"https://pith.science/api/pith-number/ZVR33JR5ZZL4YO3U7IL46NTLC5/graph.json","events_json":"https://pith.science/api/pith-number/ZVR33JR5ZZL4YO3U7IL46NTLC5/events.json","paper":"https://pith.science/paper/ZVR33JR5"},"agent_actions":{"view_html":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5","download_json":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5.json","view_paper":"https://pith.science/paper/ZVR33JR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04960&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVR33JR5ZZL4YO3U7IL46NTLC5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVR33JR5ZZL4YO3U7IL46NTLC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5/action/storage_attestation","attest_author":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5/action/author_attestation","sign_citation":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5/action/citation_signature","submit_replication":"https://pith.science/pith/ZVR33JR5ZZL4YO3U7IL46NTLC5/action/replication_record"}},"created_at":"2026-07-05T08:32:40.431413+00:00","updated_at":"2026-07-05T08:32:40.431413+00:00"}