{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AI36HMJP6MQYRRROTKQ46KFFKP","short_pith_number":"pith:AI36HMJP","schema_version":"1.0","canonical_sha256":"0237e3b12ff32188c62e9aa1cf28a553d346f86596049debbefca6a81832d924","source":{"kind":"arxiv","id":"2308.12030","version":2},"attestation_state":"computed","paper":{"title":"Prompt-Based Length Controlled Generation with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lifeng Shang, Qun Liu, Renlong Jie, Xiaojun Meng, Xin Jiang","submitted_at":"2023-08-23T09:43:10Z","abstract_excerpt":"Large language models (LLMs) like ChatGPT and GPT-4 have attracted great attention given their surprising performance on a wide range of NLP tasks. Length controlled generation of LLMs emerges as an important topic, which enables users to fully leverage the capability of LLMs in more real-world scenarios like generating a proper answer or essay of a desired length. In addition, the autoregressive generation in LLMs is extremely time-consuming, while the ability of controlling this generated length can reduce the inference cost by limiting the length. Therefore, we propose a prompt-based length"},"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":"2308.12030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:43:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3f357f9b8a099114e01b2844ecabba20c1568a8a87dc98c6becb721fc7fc4834","abstract_canon_sha256":"05d9518bde85bc42a8c28131af355f1333881e26662cfe27e67ef34f4ff655a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:58.417472Z","signature_b64":"6N4h68Mg5Wscg6jP02dFYPn64HP3AQfTX5ihfaKKUS/wJ+pLaElZTm0MuIGCXLBswJz7LzWAcncVDcaS8aN6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0237e3b12ff32188c62e9aa1cf28a553d346f86596049debbefca6a81832d924","last_reissued_at":"2026-07-05T06:55:58.416978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:58.416978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-Based Length Controlled Generation with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lifeng Shang, Qun Liu, Renlong Jie, Xiaojun Meng, Xin Jiang","submitted_at":"2023-08-23T09:43:10Z","abstract_excerpt":"Large language models (LLMs) like ChatGPT and GPT-4 have attracted great attention given their surprising performance on a wide range of NLP tasks. Length controlled generation of LLMs emerges as an important topic, which enables users to fully leverage the capability of LLMs in more real-world scenarios like generating a proper answer or essay of a desired length. In addition, the autoregressive generation in LLMs is extremely time-consuming, while the ability of controlling this generated length can reduce the inference cost by limiting the length. Therefore, we propose a prompt-based length"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12030","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/2308.12030/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":"2308.12030","created_at":"2026-07-05T06:55:58.417038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12030v2","created_at":"2026-07-05T06:55:58.417038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12030","created_at":"2026-07-05T06:55:58.417038+00:00"},{"alias_kind":"pith_short_12","alias_value":"AI36HMJP6MQY","created_at":"2026-07-05T06:55:58.417038+00:00"},{"alias_kind":"pith_short_16","alias_value":"AI36HMJP6MQYRRRO","created_at":"2026-07-05T06:55:58.417038+00:00"},{"alias_kind":"pith_short_8","alias_value":"AI36HMJP","created_at":"2026-07-05T06:55:58.417038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.22267","citing_title":"TiCo: Time-Controllable Spoken Dialogue Model","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP","json":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP.json","graph_json":"https://pith.science/api/pith-number/AI36HMJP6MQYRRROTKQ46KFFKP/graph.json","events_json":"https://pith.science/api/pith-number/AI36HMJP6MQYRRROTKQ46KFFKP/events.json","paper":"https://pith.science/paper/AI36HMJP"},"agent_actions":{"view_html":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP","download_json":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP.json","view_paper":"https://pith.science/paper/AI36HMJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12030&json=true","fetch_graph":"https://pith.science/api/pith-number/AI36HMJP6MQYRRROTKQ46KFFKP/graph.json","fetch_events":"https://pith.science/api/pith-number/AI36HMJP6MQYRRROTKQ46KFFKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP/action/storage_attestation","attest_author":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP/action/author_attestation","sign_citation":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP/action/citation_signature","submit_replication":"https://pith.science/pith/AI36HMJP6MQYRRROTKQ46KFFKP/action/replication_record"}},"created_at":"2026-07-05T06:55:58.417038+00:00","updated_at":"2026-07-05T06:55:58.417038+00:00"}