{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ERAR5JAR5Q6E3BHXM7MUI5DZ3","short_pith_number":"pith:7ERAR5JA","schema_version":"1.0","canonical_sha256":"f92208f5208f61e26c27bb3eca23a3ced68a98577f7fb0dfbbbe246309a4ff0f","source":{"kind":"arxiv","id":"2402.18013","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haohao Luo, Jiarui Ouyang, Tianhao Liao, Ying Shen, Yuwen Liu, Zhe Xu, Zihao Yi","submitted_at":"2024-02-28T03:16:44Z","abstract_excerpt":"This survey provides a comprehensive review of research on multi-turn dialogue systems, with a particular focus on multi-turn dialogue systems based on large language models (LLMs). This paper aims to (a) give a summary of existing LLMs and approaches for adapting LLMs to downstream tasks; (b) elaborate recent advances in multi-turn dialogue systems, covering both LLM-based open-domain dialogue (ODD) and task-oriented dialogue (TOD) systems, along with datasets and evaluation metrics; (c) discuss some future emphasis and recent research problems arising from the development of LLMs and the inc"},"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":"2402.18013","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T03:16:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"40d2c1aff12f4507cf3120fc838cda3bfce0a29ebc17d99b0cc98e2180842b45","abstract_canon_sha256":"aceb5e1e250e9533ede2e36eea66efea1f9c50d6821cea982632e17fb1c6f4d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:07.741858Z","signature_b64":"8O5ndldFz8GOZJgsRO5Rs6UpPZhZ6mf+iBb/ASdK0Xxjz6y6bwlV94sXuCN7/80nwdbyxAfgQfHAh5uJTrEdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92208f5208f61e26c27bb3eca23a3ced68a98577f7fb0dfbbbe246309a4ff0f","last_reissued_at":"2026-07-05T11:54:07.741404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:07.741404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haohao Luo, Jiarui Ouyang, Tianhao Liao, Ying Shen, Yuwen Liu, Zhe Xu, Zihao Yi","submitted_at":"2024-02-28T03:16:44Z","abstract_excerpt":"This survey provides a comprehensive review of research on multi-turn dialogue systems, with a particular focus on multi-turn dialogue systems based on large language models (LLMs). This paper aims to (a) give a summary of existing LLMs and approaches for adapting LLMs to downstream tasks; (b) elaborate recent advances in multi-turn dialogue systems, covering both LLM-based open-domain dialogue (ODD) and task-oriented dialogue (TOD) systems, along with datasets and evaluation metrics; (c) discuss some future emphasis and recent research problems arising from the development of LLMs and the inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18013","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/2402.18013/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":"2402.18013","created_at":"2026-07-05T11:54:07.741463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18013v2","created_at":"2026-07-05T11:54:07.741463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18013","created_at":"2026-07-05T11:54:07.741463+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ERAR5JAR5Q6","created_at":"2026-07-05T11:54:07.741463+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ERAR5JAR5Q6E3BH","created_at":"2026-07-05T11:54:07.741463+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ERAR5JA","created_at":"2026-07-05T11:54:07.741463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29563","citing_title":"Coverage-Driven KV Cache Eviction for Efficient and Improved Inference of LLM","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31073","citing_title":"ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23294","citing_title":"NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inference","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2502.01068","citing_title":"FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":244,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18768","citing_title":"ClinQueryAgent: A Conversational Agent for Population Health Management","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01449","citing_title":"LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2407.11550","citing_title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11317","citing_title":"SOMA: Efficient Multi-turn LLM Serving via Small Language Model","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23345","citing_title":"Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03375","citing_title":"Tutti: Making SSD-Backed KV Cache Practical for Long-Context LLM Serving","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3","json":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3.json","graph_json":"https://pith.science/api/pith-number/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/graph.json","events_json":"https://pith.science/api/pith-number/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/events.json","paper":"https://pith.science/paper/7ERAR5JA"},"agent_actions":{"view_html":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3","download_json":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3.json","view_paper":"https://pith.science/paper/7ERAR5JA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18013&json=true","fetch_graph":"https://pith.science/api/pith-number/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/action/storage_attestation","attest_author":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/action/author_attestation","sign_citation":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/action/citation_signature","submit_replication":"https://pith.science/pith/7ERAR5JAR5Q6E3BHXM7MUI5DZ3/action/replication_record"}},"created_at":"2026-07-05T11:54:07.741463+00:00","updated_at":"2026-07-05T11:54:07.741463+00:00"}