{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GGAA57NHQERF7HKIPHNGQUX6AX","short_pith_number":"pith:GGAA57NH","schema_version":"1.0","canonical_sha256":"31800efda781225f9d4879da6852fe05ebbec273bf291d24ed534b30435d2b6b","source":{"kind":"arxiv","id":"2505.24251","version":1},"attestation_state":"computed","paper":{"title":"Proactive Guidance of Multi-Turn Conversation in Industrial Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Junfeng Wang, Li Gao, Shuaiqiang Wang, Xiao Li, Xiaoyang Wang, Xiaoyu Li, Yiding Liu","submitted_at":"2025-05-30T06:16:30Z","abstract_excerpt":"The evolution of Large Language Models (LLMs) has significantly advanced multi-turn conversation systems, emphasizing the need for proactive guidance to enhance users' interactions. However, these systems face challenges in dynamically adapting to shifts in users' goals and maintaining low latency for real-time interactions. In the Baidu Search AI assistant, an industrial-scale multi-turn search system, we propose a novel two-phase framework to provide proactive guidance. The first phase, Goal-adaptive Supervised Fine-Tuning (G-SFT), employs a goal adaptation agent that dynamically adapts to u"},"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":"2505.24251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T06:16:30Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"ab8477eb2415584b4fe2af683f5efcbce440f172f1a32735532b2588044c0146","abstract_canon_sha256":"9cd4a1d4c7169519201190cc4fde26b1a7392f20590c12f2d2d1e60573c97373"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:45.156524Z","signature_b64":"1msXe2Jxr2d7aCj357I6PVLWDxmNHW96aLoiGzjjNIrpnHcz28Sxf1DnqqfRjxsnQkmJveo4P4y2KsQeb37ICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31800efda781225f9d4879da6852fe05ebbec273bf291d24ed534b30435d2b6b","last_reissued_at":"2026-07-05T11:12:45.155970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:45.155970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proactive Guidance of Multi-Turn Conversation in Industrial Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Junfeng Wang, Li Gao, Shuaiqiang Wang, Xiao Li, Xiaoyang Wang, Xiaoyu Li, Yiding Liu","submitted_at":"2025-05-30T06:16:30Z","abstract_excerpt":"The evolution of Large Language Models (LLMs) has significantly advanced multi-turn conversation systems, emphasizing the need for proactive guidance to enhance users' interactions. However, these systems face challenges in dynamically adapting to shifts in users' goals and maintaining low latency for real-time interactions. In the Baidu Search AI assistant, an industrial-scale multi-turn search system, we propose a novel two-phase framework to provide proactive guidance. The first phase, Goal-adaptive Supervised Fine-Tuning (G-SFT), employs a goal adaptation agent that dynamically adapts to u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24251","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/2505.24251/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":"2505.24251","created_at":"2026-07-05T11:12:45.156031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24251v1","created_at":"2026-07-05T11:12:45.156031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24251","created_at":"2026-07-05T11:12:45.156031+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGAA57NHQERF","created_at":"2026-07-05T11:12:45.156031+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGAA57NHQERF7HKI","created_at":"2026-07-05T11:12:45.156031+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGAA57NH","created_at":"2026-07-05T11:12:45.156031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18375","citing_title":"IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX","json":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX.json","graph_json":"https://pith.science/api/pith-number/GGAA57NHQERF7HKIPHNGQUX6AX/graph.json","events_json":"https://pith.science/api/pith-number/GGAA57NHQERF7HKIPHNGQUX6AX/events.json","paper":"https://pith.science/paper/GGAA57NH"},"agent_actions":{"view_html":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX","download_json":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX.json","view_paper":"https://pith.science/paper/GGAA57NH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24251&json=true","fetch_graph":"https://pith.science/api/pith-number/GGAA57NHQERF7HKIPHNGQUX6AX/graph.json","fetch_events":"https://pith.science/api/pith-number/GGAA57NHQERF7HKIPHNGQUX6AX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX/action/storage_attestation","attest_author":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX/action/author_attestation","sign_citation":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX/action/citation_signature","submit_replication":"https://pith.science/pith/GGAA57NHQERF7HKIPHNGQUX6AX/action/replication_record"}},"created_at":"2026-07-05T11:12:45.156031+00:00","updated_at":"2026-07-05T11:12:45.156031+00:00"}