{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TYK63A66NF6QL76FM4TFXIKP4D","short_pith_number":"pith:TYK63A66","schema_version":"1.0","canonical_sha256":"9e15ed83de697d05ffc567265ba14fe0fb10c68e0adea3018d5d7869913951c4","source":{"kind":"arxiv","id":"2406.17534","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiyao Chen, Liangyue Li, Meishan Zhang, Mengjia Wang, Min Zhang, Yu Zhao, Zulong Chen","submitted_at":"2024-06-25T13:19:41Z","abstract_excerpt":"Hierarchical text classification (HTC) is an important task with broad applications, while few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely-ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Pa"},"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":"2406.17534","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T13:19:41Z","cross_cats_sorted":[],"title_canon_sha256":"ddb95e26022f6b94a6d6d0f383c1883faec976df391086c94605700236a612c8","abstract_canon_sha256":"a41aee29b88935377c0f9fd46a3d83bcd9c3088d2c2151cb15698c1d089218a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:11.947952Z","signature_b64":"m2KUYBi9VCt162Es/IV958Jh/7ZEsNFuASxU8PRyuSHajbzPNISSeNiHpgbNkEItXPAZjo4W7bGr17YhZHlGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e15ed83de697d05ffc567265ba14fe0fb10c68e0adea3018d5d7869913951c4","last_reissued_at":"2026-07-05T08:38:11.947499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:11.947499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiyao Chen, Liangyue Li, Meishan Zhang, Mengjia Wang, Min Zhang, Yu Zhao, Zulong Chen","submitted_at":"2024-06-25T13:19:41Z","abstract_excerpt":"Hierarchical text classification (HTC) is an important task with broad applications, while few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achieved significant success in few-shot learning, it is not as effective for HTC because of the expansive hierarchical label sets and extremely-ambiguous labels. In this work, we introduce the first ICL-based framework with LLM for few-shot HTC. We exploit a retrieval database to identify relevant demonstrations, and an iterative policy to manage multi-layer hierarchical labels. Pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17534","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/2406.17534/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":"2406.17534","created_at":"2026-07-05T08:38:11.947561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17534v2","created_at":"2026-07-05T08:38:11.947561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17534","created_at":"2026-07-05T08:38:11.947561+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYK63A66NF6Q","created_at":"2026-07-05T08:38:11.947561+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYK63A66NF6QL76F","created_at":"2026-07-05T08:38:11.947561+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYK63A66","created_at":"2026-07-05T08:38:11.947561+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03127","citing_title":"Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D","json":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D.json","graph_json":"https://pith.science/api/pith-number/TYK63A66NF6QL76FM4TFXIKP4D/graph.json","events_json":"https://pith.science/api/pith-number/TYK63A66NF6QL76FM4TFXIKP4D/events.json","paper":"https://pith.science/paper/TYK63A66"},"agent_actions":{"view_html":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D","download_json":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D.json","view_paper":"https://pith.science/paper/TYK63A66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17534&json=true","fetch_graph":"https://pith.science/api/pith-number/TYK63A66NF6QL76FM4TFXIKP4D/graph.json","fetch_events":"https://pith.science/api/pith-number/TYK63A66NF6QL76FM4TFXIKP4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D/action/storage_attestation","attest_author":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D/action/author_attestation","sign_citation":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D/action/citation_signature","submit_replication":"https://pith.science/pith/TYK63A66NF6QL76FM4TFXIKP4D/action/replication_record"}},"created_at":"2026-07-05T08:38:11.947561+00:00","updated_at":"2026-07-05T08:38:11.947561+00:00"}