{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BWOSH3PM2WJLWP6ANDBTGFJDIB","short_pith_number":"pith:BWOSH3PM","schema_version":"1.0","canonical_sha256":"0d9d23edecd592bb3fc068c3331523407f255f921531b087ecf4ac070cd5aebc","source":{"kind":"arxiv","id":"2502.12813","version":1},"attestation_state":"computed","paper":{"title":"Simulating User Diversity in Task-Oriented Dialogue Systems using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adnan Ahmad, Sebastian M\\\"oller, Stefan Hillmann","submitted_at":"2025-02-18T12:20:16Z","abstract_excerpt":"In this study, we explore the application of Large Language Models (LLMs) for generating synthetic users and simulating user conversations with a task-oriented dialogue system and present detailed results and their analysis. We propose a comprehensive novel approach to user simulation technique that uses LLMs to create diverse user profiles, set goals, engage in multi-turn dialogues, and evaluate the conversation success. We employ two proprietary LLMs, namely GPT-4o and GPT-o1 (Achiam et al., 2023), to generate a heterogeneous base of user profiles, characterized by varied demographics, multi"},"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":"2502.12813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T12:20:16Z","cross_cats_sorted":[],"title_canon_sha256":"ee08a9e55d1984b1c6c443b3cb88ab64e77509767135ce47eb2f61d5c44e2959","abstract_canon_sha256":"9dee5913d8256fb19d12178279ebdd3638bfebdbd1810b01ae0e27941c4e3e6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:24.597750Z","signature_b64":"7wUkiKaQ1Herx/ckjux/HGZy2bqM7LpInAladDgF7fJuOwgOWRNuTd5fLgx9t3y+/vtjzDlhqObbF1/Z/ULHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d9d23edecd592bb3fc068c3331523407f255f921531b087ecf4ac070cd5aebc","last_reissued_at":"2026-07-05T10:16:24.597128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:24.597128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulating User Diversity in Task-Oriented Dialogue Systems using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adnan Ahmad, Sebastian M\\\"oller, Stefan Hillmann","submitted_at":"2025-02-18T12:20:16Z","abstract_excerpt":"In this study, we explore the application of Large Language Models (LLMs) for generating synthetic users and simulating user conversations with a task-oriented dialogue system and present detailed results and their analysis. We propose a comprehensive novel approach to user simulation technique that uses LLMs to create diverse user profiles, set goals, engage in multi-turn dialogues, and evaluate the conversation success. We employ two proprietary LLMs, namely GPT-4o and GPT-o1 (Achiam et al., 2023), to generate a heterogeneous base of user profiles, characterized by varied demographics, multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12813","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/2502.12813/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":"2502.12813","created_at":"2026-07-05T10:16:24.597256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12813v1","created_at":"2026-07-05T10:16:24.597256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12813","created_at":"2026-07-05T10:16:24.597256+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWOSH3PM2WJL","created_at":"2026-07-05T10:16:24.597256+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWOSH3PM2WJLWP6A","created_at":"2026-07-05T10:16:24.597256+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWOSH3PM","created_at":"2026-07-05T10:16:24.597256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03318","citing_title":"Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02908","citing_title":"WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08118","citing_title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB","json":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB.json","graph_json":"https://pith.science/api/pith-number/BWOSH3PM2WJLWP6ANDBTGFJDIB/graph.json","events_json":"https://pith.science/api/pith-number/BWOSH3PM2WJLWP6ANDBTGFJDIB/events.json","paper":"https://pith.science/paper/BWOSH3PM"},"agent_actions":{"view_html":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB","download_json":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB.json","view_paper":"https://pith.science/paper/BWOSH3PM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12813&json=true","fetch_graph":"https://pith.science/api/pith-number/BWOSH3PM2WJLWP6ANDBTGFJDIB/graph.json","fetch_events":"https://pith.science/api/pith-number/BWOSH3PM2WJLWP6ANDBTGFJDIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB/action/storage_attestation","attest_author":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB/action/author_attestation","sign_citation":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB/action/citation_signature","submit_replication":"https://pith.science/pith/BWOSH3PM2WJLWP6ANDBTGFJDIB/action/replication_record"}},"created_at":"2026-07-05T10:16:24.597256+00:00","updated_at":"2026-07-05T10:16:24.597256+00:00"}