{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OLVCE22VTD4PPRA4KFZTERGGIF","short_pith_number":"pith:OLVCE22V","schema_version":"1.0","canonical_sha256":"72ea226b5598f8f7c41c51733244c6417dce6ef362272b9ebcf48efe776d0675","source":{"kind":"arxiv","id":"2405.06373","version":4},"attestation_state":"computed","paper":{"title":"LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chan-Hung Yu, Hung-yi Lee, Li-Chun Lu, Shao-Hua Sun, Shou-Jen Chen, Tsung-Min Pai","submitted_at":"2024-05-10T10:19:14Z","abstract_excerpt":"Large language models (LLMs) have shown exceptional proficiency in natural language processing but often fall short of generating creative and original responses to open-ended questions. To enhance LLM creativity, our key insight is to emulate the human process of inducing collective creativity through engaging discussions with participants from diverse backgrounds and perspectives. To this end, we propose LLM Discussion, a three-phase discussion framework that facilitates vigorous and diverging idea exchanges and ensures convergence to creative answers. Moreover, we adopt a role-playing techn"},"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":"2405.06373","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-10T10:19:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac275598875bf07cd44459f6199b07d36dc136dc30df15381ec0579d28f6ec0a","abstract_canon_sha256":"dc4ecb9d2fab4dafd6547a83369158eb75a03cdb1cc305892c55e3125aa10129"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:22.540042Z","signature_b64":"rMW3i7IDxr5RtbM5t5FdoV6Wmj8uP+90gCPhSFWFpfBSJXmHzXgjNyLqXfJXaWLtdrI0gT6sLiA81DqD9stRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72ea226b5598f8f7c41c51733244c6417dce6ef362272b9ebcf48efe776d0675","last_reissued_at":"2026-07-05T08:53:22.539637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:22.539637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chan-Hung Yu, Hung-yi Lee, Li-Chun Lu, Shao-Hua Sun, Shou-Jen Chen, Tsung-Min Pai","submitted_at":"2024-05-10T10:19:14Z","abstract_excerpt":"Large language models (LLMs) have shown exceptional proficiency in natural language processing but often fall short of generating creative and original responses to open-ended questions. To enhance LLM creativity, our key insight is to emulate the human process of inducing collective creativity through engaging discussions with participants from diverse backgrounds and perspectives. To this end, we propose LLM Discussion, a three-phase discussion framework that facilitates vigorous and diverging idea exchanges and ensures convergence to creative answers. Moreover, we adopt a role-playing techn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06373","kind":"arxiv","version":4},"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/2405.06373/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":"2405.06373","created_at":"2026-07-05T08:53:22.539691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06373v4","created_at":"2026-07-05T08:53:22.539691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06373","created_at":"2026-07-05T08:53:22.539691+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLVCE22VTD4P","created_at":"2026-07-05T08:53:22.539691+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLVCE22VTD4PPRA4","created_at":"2026-07-05T08:53:22.539691+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLVCE22V","created_at":"2026-07-05T08:53:22.539691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08068","citing_title":"DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10113","citing_title":"Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2411.00585","citing_title":"Fairness Testing of Large Language Models in Role-Playing","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15408","citing_title":"Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02350","citing_title":"Context Learning for Multi-Agent Discussion","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF","json":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF.json","graph_json":"https://pith.science/api/pith-number/OLVCE22VTD4PPRA4KFZTERGGIF/graph.json","events_json":"https://pith.science/api/pith-number/OLVCE22VTD4PPRA4KFZTERGGIF/events.json","paper":"https://pith.science/paper/OLVCE22V"},"agent_actions":{"view_html":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF","download_json":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF.json","view_paper":"https://pith.science/paper/OLVCE22V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06373&json=true","fetch_graph":"https://pith.science/api/pith-number/OLVCE22VTD4PPRA4KFZTERGGIF/graph.json","fetch_events":"https://pith.science/api/pith-number/OLVCE22VTD4PPRA4KFZTERGGIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF/action/storage_attestation","attest_author":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF/action/author_attestation","sign_citation":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF/action/citation_signature","submit_replication":"https://pith.science/pith/OLVCE22VTD4PPRA4KFZTERGGIF/action/replication_record"}},"created_at":"2026-07-05T08:53:22.539691+00:00","updated_at":"2026-07-05T08:53:22.539691+00:00"}