{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LEASKPAMZ477C2QK27CP4LDKG2","short_pith_number":"pith:LEASKPAM","schema_version":"1.0","canonical_sha256":"5901253c0ccf3ff16a0ad7c4fe2c6a36a7379a11abac4a1e9ae42cce5d80aea7","source":{"kind":"arxiv","id":"2305.11595","version":3},"attestation_state":"computed","paper":{"title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Kai Xiong, Ting Liu, Xiao Ding, Yixin Cao","submitted_at":"2023-05-19T11:15:33Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we complementarily explore the inter-consistency among multiple LLMs for collaboration. To examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal, we focus on commonsense reasoning, and introduce a formal debate framework (FORD) to conduct a three-stage debate among LLMs with real-world scenarios alignment: fair debate, mismatched debate,"},"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":"2305.11595","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T11:15:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f322495aa02b3b15ada7f54cee763622e1f363c1f2ac7d9a853100cbedd8e4c","abstract_canon_sha256":"72312114cda0d48b4df988bfd51871c2cf82fe31628e60147c78826923439094"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:05.828787Z","signature_b64":"NYLDbiil598WoNepvcQ7Uv4oIF0dfHI2lOlYpMFWJdN4X+L8uvcSPrX992c4EyzYa0XUdFgV8nOEURu42AaXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5901253c0ccf3ff16a0ad7c4fe2c6a36a7379a11abac4a1e9ae42cce5d80aea7","last_reissued_at":"2026-07-05T09:35:05.828218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:05.828218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Kai Xiong, Ting Liu, Xiao Ding, Yixin Cao","submitted_at":"2023-05-19T11:15:33Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we complementarily explore the inter-consistency among multiple LLMs for collaboration. To examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal, we focus on commonsense reasoning, and introduce a formal debate framework (FORD) to conduct a three-stage debate among LLMs with real-world scenarios alignment: fair debate, mismatched debate,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11595","kind":"arxiv","version":3},"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/2305.11595/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":"2305.11595","created_at":"2026-07-05T09:35:05.828273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11595v3","created_at":"2026-07-05T09:35:05.828273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11595","created_at":"2026-07-05T09:35:05.828273+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEASKPAMZ477","created_at":"2026-07-05T09:35:05.828273+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEASKPAMZ477C2QK","created_at":"2026-07-05T09:35:05.828273+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEASKPAM","created_at":"2026-07-05T09:35:05.828273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.20260","citing_title":"Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2305.19118","citing_title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2","json":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2.json","graph_json":"https://pith.science/api/pith-number/LEASKPAMZ477C2QK27CP4LDKG2/graph.json","events_json":"https://pith.science/api/pith-number/LEASKPAMZ477C2QK27CP4LDKG2/events.json","paper":"https://pith.science/paper/LEASKPAM"},"agent_actions":{"view_html":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2","download_json":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2.json","view_paper":"https://pith.science/paper/LEASKPAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11595&json=true","fetch_graph":"https://pith.science/api/pith-number/LEASKPAMZ477C2QK27CP4LDKG2/graph.json","fetch_events":"https://pith.science/api/pith-number/LEASKPAMZ477C2QK27CP4LDKG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2/action/storage_attestation","attest_author":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2/action/author_attestation","sign_citation":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2/action/citation_signature","submit_replication":"https://pith.science/pith/LEASKPAMZ477C2QK27CP4LDKG2/action/replication_record"}},"created_at":"2026-07-05T09:35:05.828273+00:00","updated_at":"2026-07-05T09:35:05.828273+00:00"}