{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DB5QXJSEBSGKHXZILXCZI4AJP4","short_pith_number":"pith:DB5QXJSE","schema_version":"1.0","canonical_sha256":"187b0ba6440c8ca3df285dc59470097f166080c75cf4d4c692d8ed062311a7d1","source":{"kind":"arxiv","id":"2507.12370","version":1},"attestation_state":"computed","paper":{"title":"Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Ana Davila, Jacinto Colan, Yasuhisa Hasegawa","submitted_at":"2025-07-16T16:15:25Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user requests processed by LLMs. To address these challenges, this paper introduces and evaluates a multi-agent debate framework designed to enhance detection and resolution capabilities beyond single models. The framework consists of three LLM architectures (Llama3-8B, Gemma2-9B, and Mistral-7B variants) and a dataset with diverse ambiguities. The debate framewo"},"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":"2507.12370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T16:15:25Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"88710cc14b720179f488cac545740e0f6aa597ca2de10f8413c956ad26249148","abstract_canon_sha256":"47716a633aca1cf9d2608c0579005e51b573ba661a3e14820608b2ad72236397"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:19.129826Z","signature_b64":"Q1AyQ8wOlcmjIz2Y+QWxX1cpfsSwFrfj9dwUGaysiqOl9yb/e4UDLm4U8BcsTa4GUmPDv+K/zktaVnrn8aE2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"187b0ba6440c8ca3df285dc59470097f166080c75cf4d4c692d8ed062311a7d1","last_reissued_at":"2026-07-05T11:38:19.129303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:19.129303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Ana Davila, Jacinto Colan, Yasuhisa Hasegawa","submitted_at":"2025-07-16T16:15:25Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user requests processed by LLMs. To address these challenges, this paper introduces and evaluates a multi-agent debate framework designed to enhance detection and resolution capabilities beyond single models. The framework consists of three LLM architectures (Llama3-8B, Gemma2-9B, and Mistral-7B variants) and a dataset with diverse ambiguities. The debate framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12370","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/2507.12370/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":"2507.12370","created_at":"2026-07-05T11:38:19.129379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12370v1","created_at":"2026-07-05T11:38:19.129379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12370","created_at":"2026-07-05T11:38:19.129379+00:00"},{"alias_kind":"pith_short_12","alias_value":"DB5QXJSEBSGK","created_at":"2026-07-05T11:38:19.129379+00:00"},{"alias_kind":"pith_short_16","alias_value":"DB5QXJSEBSGKHXZI","created_at":"2026-07-05T11:38:19.129379+00:00"},{"alias_kind":"pith_short_8","alias_value":"DB5QXJSE","created_at":"2026-07-05T11:38:19.129379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4","json":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4.json","graph_json":"https://pith.science/api/pith-number/DB5QXJSEBSGKHXZILXCZI4AJP4/graph.json","events_json":"https://pith.science/api/pith-number/DB5QXJSEBSGKHXZILXCZI4AJP4/events.json","paper":"https://pith.science/paper/DB5QXJSE"},"agent_actions":{"view_html":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4","download_json":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4.json","view_paper":"https://pith.science/paper/DB5QXJSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12370&json=true","fetch_graph":"https://pith.science/api/pith-number/DB5QXJSEBSGKHXZILXCZI4AJP4/graph.json","fetch_events":"https://pith.science/api/pith-number/DB5QXJSEBSGKHXZILXCZI4AJP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4/action/storage_attestation","attest_author":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4/action/author_attestation","sign_citation":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4/action/citation_signature","submit_replication":"https://pith.science/pith/DB5QXJSEBSGKHXZILXCZI4AJP4/action/replication_record"}},"created_at":"2026-07-05T11:38:19.129379+00:00","updated_at":"2026-07-05T11:38:19.129379+00:00"}