{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MFGN56V6J5WUKNHGPSLDS62KS7","short_pith_number":"pith:MFGN56V6","schema_version":"1.0","canonical_sha256":"614cdefabe4f6d4534e67c96397b4a97d560ca50197610ffe0d1ca6843bf60fc","source":{"kind":"arxiv","id":"2502.13474","version":1},"attestation_state":"computed","paper":{"title":"Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyang Lyu, Chenyu Zhu, Guanhua Chen, Kaifu Zhang, Longyue Wang, Weihua Luo, Xue Yang, Yefeng Liu","submitted_at":"2025-02-19T06:56:02Z","abstract_excerpt":"Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing. Supervised fine-tuning methods are often employed for this task due to their simplicity and effectiveness. However, they still have some limitations: low rank adaptation (LoRA) only fine-tunes a few parameters and has suboptimal control effects, while full fine-tuning (FFT) requires significant computational resources and is susceptible to overfitting, particularly when data is limited. Moreover, existing works typi"},"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":"2502.13474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T06:56:02Z","cross_cats_sorted":[],"title_canon_sha256":"a48732d92c602a490bcc565a981121bf205d93e5b01045ba266e0548bfb45095","abstract_canon_sha256":"6aedb1e5a71da34e4f7bc0e6fa214837119e35c604f8ff4afbcdec3ae3d3d462"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:47.764856Z","signature_b64":"tL/FZfTzY5eRZXf19W24LIXJ9eslWMFkAA5EPYL3RC5XVdZnLTZWiszwoYoKTJ7HZn7jn0sBXy9rzKy+o23NBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"614cdefabe4f6d4534e67c96397b4a97d560ca50197610ffe0d1ca6843bf60fc","last_reissued_at":"2026-07-05T10:16:47.764414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:47.764414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyang Lyu, Chenyu Zhu, Guanhua Chen, Kaifu Zhang, Longyue Wang, Weihua Luo, Xue Yang, Yefeng Liu","submitted_at":"2025-02-19T06:56:02Z","abstract_excerpt":"Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing. Supervised fine-tuning methods are often employed for this task due to their simplicity and effectiveness. However, they still have some limitations: low rank adaptation (LoRA) only fine-tunes a few parameters and has suboptimal control effects, while full fine-tuning (FFT) requires significant computational resources and is susceptible to overfitting, particularly when data is limited. Moreover, existing works typi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13474","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/2502.13474/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":"2502.13474","created_at":"2026-07-05T10:16:47.764477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13474v1","created_at":"2026-07-05T10:16:47.764477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13474","created_at":"2026-07-05T10:16:47.764477+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFGN56V6J5WU","created_at":"2026-07-05T10:16:47.764477+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFGN56V6J5WUKNHG","created_at":"2026-07-05T10:16:47.764477+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFGN56V6","created_at":"2026-07-05T10:16:47.764477+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/MFGN56V6J5WUKNHGPSLDS62KS7","json":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7.json","graph_json":"https://pith.science/api/pith-number/MFGN56V6J5WUKNHGPSLDS62KS7/graph.json","events_json":"https://pith.science/api/pith-number/MFGN56V6J5WUKNHGPSLDS62KS7/events.json","paper":"https://pith.science/paper/MFGN56V6"},"agent_actions":{"view_html":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7","download_json":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7.json","view_paper":"https://pith.science/paper/MFGN56V6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13474&json=true","fetch_graph":"https://pith.science/api/pith-number/MFGN56V6J5WUKNHGPSLDS62KS7/graph.json","fetch_events":"https://pith.science/api/pith-number/MFGN56V6J5WUKNHGPSLDS62KS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7/action/storage_attestation","attest_author":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7/action/author_attestation","sign_citation":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7/action/citation_signature","submit_replication":"https://pith.science/pith/MFGN56V6J5WUKNHGPSLDS62KS7/action/replication_record"}},"created_at":"2026-07-05T10:16:47.764477+00:00","updated_at":"2026-07-05T10:16:47.764477+00:00"}