{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:53CEWZIEQW33VPLQYTGZS4RBYH","short_pith_number":"pith:53CEWZIE","schema_version":"1.0","canonical_sha256":"eec44b650485b7babd70c4cd997221c1c4305e846a58978be86b6b602e4fa90d","source":{"kind":"arxiv","id":"2305.13626","version":2},"attestation_state":"computed","paper":{"title":"Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongru Wang, Liang Chen, Lizi Liao, Tat-Seng Chua, Wenqiang Lei, Yang Deng","submitted_at":"2023-05-23T02:49:35Z","abstract_excerpt":"Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, despite their impressive capabilities, they still possess limitations, such as providing randomly-guessed answers to ambiguous queries or failing to refuse users' requests, both of which are considered aspects of a conversational agent's proactivity. This raises the question of whether LLM-based conversational systems are equipped to handle proactive dialogue problems. In this work, we conduct a comprehensive analysis of LLM-base"},"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":"2305.13626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T02:49:35Z","cross_cats_sorted":[],"title_canon_sha256":"8c7da5ec203db698da7f198ffb5a3de76c07d803e4f46b0ddb6d6dae66d280ed","abstract_canon_sha256":"110b134cd3a0ff1c09b97786e4b3fc49e229118e3a528f887a6b9f0700b6711e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:44.627295Z","signature_b64":"9bgK6b/eqjPldinnlSTZ1vCTW2ZSd45SR0DmNcXr1AqT0hUVClFxTRNN5bLx2hzqMzsEPiJiVD+KNkvvYIpgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eec44b650485b7babd70c4cd997221c1c4305e846a58978be86b6b602e4fa90d","last_reissued_at":"2026-07-05T07:00:44.626814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:44.626814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongru Wang, Liang Chen, Lizi Liao, Tat-Seng Chua, Wenqiang Lei, Yang Deng","submitted_at":"2023-05-23T02:49:35Z","abstract_excerpt":"Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, despite their impressive capabilities, they still possess limitations, such as providing randomly-guessed answers to ambiguous queries or failing to refuse users' requests, both of which are considered aspects of a conversational agent's proactivity. This raises the question of whether LLM-based conversational systems are equipped to handle proactive dialogue problems. In this work, we conduct a comprehensive analysis of LLM-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13626","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/2305.13626/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":"2305.13626","created_at":"2026-07-05T07:00:44.626869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13626v2","created_at":"2026-07-05T07:00:44.626869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13626","created_at":"2026-07-05T07:00:44.626869+00:00"},{"alias_kind":"pith_short_12","alias_value":"53CEWZIEQW33","created_at":"2026-07-05T07:00:44.626869+00:00"},{"alias_kind":"pith_short_16","alias_value":"53CEWZIEQW33VPLQ","created_at":"2026-07-05T07:00:44.626869+00:00"},{"alias_kind":"pith_short_8","alias_value":"53CEWZIE","created_at":"2026-07-05T07:00:44.626869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12587","citing_title":"Strategic Decision Support for AI Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01182","citing_title":"CA-BED: Conversation-Aware Bayesian Experimental Design","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05386","citing_title":"BALAR : A Bayesian Agentic Loop for Active Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08898","citing_title":"Omakase: proactive assistance with actionable suggestions for evolving scientific research projects","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH","json":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH.json","graph_json":"https://pith.science/api/pith-number/53CEWZIEQW33VPLQYTGZS4RBYH/graph.json","events_json":"https://pith.science/api/pith-number/53CEWZIEQW33VPLQYTGZS4RBYH/events.json","paper":"https://pith.science/paper/53CEWZIE"},"agent_actions":{"view_html":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH","download_json":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH.json","view_paper":"https://pith.science/paper/53CEWZIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13626&json=true","fetch_graph":"https://pith.science/api/pith-number/53CEWZIEQW33VPLQYTGZS4RBYH/graph.json","fetch_events":"https://pith.science/api/pith-number/53CEWZIEQW33VPLQYTGZS4RBYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH/action/storage_attestation","attest_author":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH/action/author_attestation","sign_citation":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH/action/citation_signature","submit_replication":"https://pith.science/pith/53CEWZIEQW33VPLQYTGZS4RBYH/action/replication_record"}},"created_at":"2026-07-05T07:00:44.626869+00:00","updated_at":"2026-07-05T07:00:44.626869+00:00"}