{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:77ZKCHWIWGDEZFYEEWFAO7NFOM","short_pith_number":"pith:77ZKCHWI","schema_version":"1.0","canonical_sha256":"fff2a11ec8b1864c9704258a077da5730266038176dd18e84ab29bb6948fc5da","source":{"kind":"arxiv","id":"2311.01677","version":2},"attestation_state":"computed","paper":{"title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Junda Lu, Kun Gai, Yihong Tang","submitted_at":"2023-11-03T02:59:56Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable breakthroughs in new dialogue capabilities by leveraging instruction tuning, which refreshes human impressions of dialogue systems. The long-standing goal of dialogue systems is to be human-like enough to establish long-term connections with users. Therefore, there has been an urgent need to evaluate LLMs as human-like dialogue systems. In this paper, we propose DialogBench, a dialogue evaluation benchmark that contains 12 dialogue tasks to probe the capabilities of LLMs as human-like dialogue systems should have. Specifically, we prompt GP"},"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":"2311.01677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T02:59:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58f06f529d22d8fa2ea75e0d053d98f3dacb1432f21b9b386413edf44ea5f39c","abstract_canon_sha256":"88607a6114159a6431e226363fc00ab82bbfa2ac560f8c9148a2e8b71665ccf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:02.759597Z","signature_b64":"yy6sIKMrYdeFZVgWPAg2lZP1Jhfc64cU9lrhZas/EagPaKd5y5dDcK4OpGD9hY3rBmLuUal76vuT/4HwC9GQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fff2a11ec8b1864c9704258a077da5730266038176dd18e84ab29bb6948fc5da","last_reissued_at":"2026-07-05T08:02:02.759062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:02.759062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Junda Lu, Kun Gai, Yihong Tang","submitted_at":"2023-11-03T02:59:56Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable breakthroughs in new dialogue capabilities by leveraging instruction tuning, which refreshes human impressions of dialogue systems. The long-standing goal of dialogue systems is to be human-like enough to establish long-term connections with users. Therefore, there has been an urgent need to evaluate LLMs as human-like dialogue systems. In this paper, we propose DialogBench, a dialogue evaluation benchmark that contains 12 dialogue tasks to probe the capabilities of LLMs as human-like dialogue systems should have. Specifically, we prompt GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01677","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/2311.01677/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":"2311.01677","created_at":"2026-07-05T08:02:02.759119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01677v2","created_at":"2026-07-05T08:02:02.759119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01677","created_at":"2026-07-05T08:02:02.759119+00:00"},{"alias_kind":"pith_short_12","alias_value":"77ZKCHWIWGDE","created_at":"2026-07-05T08:02:02.759119+00:00"},{"alias_kind":"pith_short_16","alias_value":"77ZKCHWIWGDEZFYE","created_at":"2026-07-05T08:02:02.759119+00:00"},{"alias_kind":"pith_short_8","alias_value":"77ZKCHWI","created_at":"2026-07-05T08:02:02.759119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15557","citing_title":"MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM","json":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM.json","graph_json":"https://pith.science/api/pith-number/77ZKCHWIWGDEZFYEEWFAO7NFOM/graph.json","events_json":"https://pith.science/api/pith-number/77ZKCHWIWGDEZFYEEWFAO7NFOM/events.json","paper":"https://pith.science/paper/77ZKCHWI"},"agent_actions":{"view_html":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM","download_json":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM.json","view_paper":"https://pith.science/paper/77ZKCHWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01677&json=true","fetch_graph":"https://pith.science/api/pith-number/77ZKCHWIWGDEZFYEEWFAO7NFOM/graph.json","fetch_events":"https://pith.science/api/pith-number/77ZKCHWIWGDEZFYEEWFAO7NFOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/action/storage_attestation","attest_author":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/action/author_attestation","sign_citation":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/action/citation_signature","submit_replication":"https://pith.science/pith/77ZKCHWIWGDEZFYEEWFAO7NFOM/action/replication_record"}},"created_at":"2026-07-05T08:02:02.759119+00:00","updated_at":"2026-07-05T08:02:02.759119+00:00"}