{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:42TNKDZD5U7FIKJ4363ACBPDXJ","short_pith_number":"pith:42TNKDZD","schema_version":"1.0","canonical_sha256":"e6a6d50f23ed3e54293cdfb60105e3ba7185ed9267169398533e14124952275d","source":{"kind":"arxiv","id":"2406.10505","version":1},"attestation_state":"computed","paper":{"title":"CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fuxuan Wei, Jiasheng Si, Jingxuan Zhou, Libo Qin, Qiguang Chen, Shijue Huang, Wanxiang Che, Wenpeng Lu","submitted_at":"2024-06-15T04:54:56Z","abstract_excerpt":"Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU"},"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":"2406.10505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T04:54:56Z","cross_cats_sorted":[],"title_canon_sha256":"aa62bbfb5b60d3d2f7400adbb744035c8f9bc09a4d8420de9ee5aba469b29d08","abstract_canon_sha256":"eec4a534617182fea77ba5cd549610fc87449daaf0e37479c6c41ce601eec833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:17.532348Z","signature_b64":"4IQNMcOCBX7AW1nRbuyGx5TqWx8KKnSa/EkD9lQQFZv5yIT91eoJvHT/lEkqrGFevpU/ymnD7hZHTENlqij5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a6d50f23ed3e54293cdfb60105e3ba7185ed9267169398533e14124952275d","last_reissued_at":"2026-07-05T08:32:17.531844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:17.531844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fuxuan Wei, Jiasheng Si, Jingxuan Zhou, Libo Qin, Qiguang Chen, Shijue Huang, Wanxiang Che, Wenpeng Lu","submitted_at":"2024-06-15T04:54:56Z","abstract_excerpt":"Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10505","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/2406.10505/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":"2406.10505","created_at":"2026-07-05T08:32:17.531897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10505v1","created_at":"2026-07-05T08:32:17.531897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10505","created_at":"2026-07-05T08:32:17.531897+00:00"},{"alias_kind":"pith_short_12","alias_value":"42TNKDZD5U7F","created_at":"2026-07-05T08:32:17.531897+00:00"},{"alias_kind":"pith_short_16","alias_value":"42TNKDZD5U7FIKJ4","created_at":"2026-07-05T08:32:17.531897+00:00"},{"alias_kind":"pith_short_8","alias_value":"42TNKDZD","created_at":"2026-07-05T08:32:17.531897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10104","citing_title":"RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ","json":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ.json","graph_json":"https://pith.science/api/pith-number/42TNKDZD5U7FIKJ4363ACBPDXJ/graph.json","events_json":"https://pith.science/api/pith-number/42TNKDZD5U7FIKJ4363ACBPDXJ/events.json","paper":"https://pith.science/paper/42TNKDZD"},"agent_actions":{"view_html":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ","download_json":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ.json","view_paper":"https://pith.science/paper/42TNKDZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10505&json=true","fetch_graph":"https://pith.science/api/pith-number/42TNKDZD5U7FIKJ4363ACBPDXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/42TNKDZD5U7FIKJ4363ACBPDXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ/action/storage_attestation","attest_author":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ/action/author_attestation","sign_citation":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ/action/citation_signature","submit_replication":"https://pith.science/pith/42TNKDZD5U7FIKJ4363ACBPDXJ/action/replication_record"}},"created_at":"2026-07-05T08:32:17.531897+00:00","updated_at":"2026-07-05T08:32:17.531897+00:00"}