{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3CIWFXIFMXKU3YDBPGQ7PV5JKJ","short_pith_number":"pith:3CIWFXIF","schema_version":"1.0","canonical_sha256":"d89162dd0565d54de06179a1f7d7a9527d55f7a286a5221e1226441316a3e4b7","source":{"kind":"arxiv","id":"2505.07460","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"HaoHao Han, Jiahao Zhao, Yi Chen","submitted_at":"2025-05-12T11:48:42Z","abstract_excerpt":"Large Language Models (LLMs) deliver powerful AI capabilities but face deployment challenges due to high resource costs and latency, whereas Small Language Models (SLMs) offer efficiency and deployability at the cost of reduced performance. Collaboration between LLMs and SLMs emerges as a crucial paradigm to synergistically balance these trade-offs, enabling advanced AI applications, especially on resource-constrained edge devices. This survey provides a comprehensive overview of LLM-SLM collaboration, detailing various interaction mechanisms (pipeline, routing, auxiliary, distillation, fusion"},"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":"2505.07460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T11:48:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"68b5d685e31233b20a826220deb762e68cb2bcb646235453edc0d13afb6d7342","abstract_canon_sha256":"426e7ff0997119016f4e035323850d45382436dada78c31b329d804be35666b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:48.050659Z","signature_b64":"w3WFoSIK+0Ch8mcBMBF+q4O8HAGBiDf+lXVlQCGRrw19LzFxRDYVQ8nAxEtfzvMQbMQYVL9fxJPe26QRBlL4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d89162dd0565d54de06179a1f7d7a9527d55f7a286a5221e1226441316a3e4b7","last_reissued_at":"2026-07-05T11:01:48.050194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:48.050194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"HaoHao Han, Jiahao Zhao, Yi Chen","submitted_at":"2025-05-12T11:48:42Z","abstract_excerpt":"Large Language Models (LLMs) deliver powerful AI capabilities but face deployment challenges due to high resource costs and latency, whereas Small Language Models (SLMs) offer efficiency and deployability at the cost of reduced performance. Collaboration between LLMs and SLMs emerges as a crucial paradigm to synergistically balance these trade-offs, enabling advanced AI applications, especially on resource-constrained edge devices. This survey provides a comprehensive overview of LLM-SLM collaboration, detailing various interaction mechanisms (pipeline, routing, auxiliary, distillation, fusion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07460","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/2505.07460/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":"2505.07460","created_at":"2026-07-05T11:01:48.050250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07460v1","created_at":"2026-07-05T11:01:48.050250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07460","created_at":"2026-07-05T11:01:48.050250+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CIWFXIFMXKU","created_at":"2026-07-05T11:01:48.050250+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CIWFXIFMXKU3YDB","created_at":"2026-07-05T11:01:48.050250+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CIWFXIF","created_at":"2026-07-05T11:01:48.050250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06278","citing_title":"Quality-Aware Personalized AI Service Provisioning in UAV-Assisted 6G Networks","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23695","citing_title":"Quantifying Prior Dominance in RAG Systems","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18036","citing_title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27112","citing_title":"RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07494","citing_title":"Triage: Routing Software Engineering Tasks to Cost-Effective LLM Tiers via Code Quality Signals","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ","json":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ.json","graph_json":"https://pith.science/api/pith-number/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/graph.json","events_json":"https://pith.science/api/pith-number/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/events.json","paper":"https://pith.science/paper/3CIWFXIF"},"agent_actions":{"view_html":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ","download_json":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ.json","view_paper":"https://pith.science/paper/3CIWFXIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07460&json=true","fetch_graph":"https://pith.science/api/pith-number/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/action/storage_attestation","attest_author":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/action/author_attestation","sign_citation":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/action/citation_signature","submit_replication":"https://pith.science/pith/3CIWFXIFMXKU3YDBPGQ7PV5JKJ/action/replication_record"}},"created_at":"2026-07-05T11:01:48.050250+00:00","updated_at":"2026-07-05T11:01:48.050250+00:00"}