{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z5TFBZ3F7VTJHPIGGIXOC5R2W6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6c6b54a822faa29857e3218e091d8384465b67534617e2892f7d7d081098c997","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-22T20:57:12Z","title_canon_sha256":"ed5199ffac93868326105b9408187cdaad10466f05abe59ffaa552c3fa1cd3f7"},"schema_version":"1.0","source":{"id":"2406.15938","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15938","created_at":"2026-07-05T10:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15938v4","created_at":"2026-07-05T10:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15938","created_at":"2026-07-05T10:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"Z5TFBZ3F7VTJ","created_at":"2026-07-05T10:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"Z5TFBZ3F7VTJHPIG","created_at":"2026-07-05T10:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"Z5TFBZ3F","created_at":"2026-07-05T10:14:41Z"}],"graph_snapshots":[{"event_id":"sha256:87ff477bc5b82d15be65c46f68b8dba050d9ea4609e56bb33caa1f0cb213e1d3","target":"graph","created_at":"2026-07-05T10:14:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.15938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) still lack delicate controllability over their responses, which is critical to enhancing their performance and the user experience. However, curating supervised fine-tuning (SFT) datasets to improve LLM controllability usually relies on human experts or proprietary LLMs, which requires additional costs. To bridge this gap, we propose Rule-based Data Recycling (RuleR), a data augmentation method incorporating multiple constraints into the original data samples according to predefined rules, which creates new training tasks to consolidate the controllability of LLMs.","authors_text":"Chenguang Wang, Dang Nguyen, Dianqi Li, Han Chen, Ming Li, Tianyi Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-22T20:57:12Z","title":"RuleR: Improving LLM Controllability by Rule-based Data Recycling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15938","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:890af206cec029c596a1a58864e873e67df2999077a1942e22f036ed0fe91531","target":"record","created_at":"2026-07-05T10:14:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6c6b54a822faa29857e3218e091d8384465b67534617e2892f7d7d081098c997","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-22T20:57:12Z","title_canon_sha256":"ed5199ffac93868326105b9408187cdaad10466f05abe59ffaa552c3fa1cd3f7"},"schema_version":"1.0","source":{"id":"2406.15938","kind":"arxiv","version":4}},"canonical_sha256":"cf6650e765fd6693bd06322ee1763ab7992ece337e5b7e40f035a555b144308e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf6650e765fd6693bd06322ee1763ab7992ece337e5b7e40f035a555b144308e","first_computed_at":"2026-07-05T10:14:41.891860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:41.891860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B97ykk7OLEKu1M9/xbbxzv8wof23DF/XDg20SyRBbanbyQ571ZV1lGSRkHFDDJ59cQtuEe7h59FVgGYdnSLDAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:41.892378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15938","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:890af206cec029c596a1a58864e873e67df2999077a1942e22f036ed0fe91531","sha256:87ff477bc5b82d15be65c46f68b8dba050d9ea4609e56bb33caa1f0cb213e1d3"],"state_sha256":"9f92ce681b2557cf9d002372bfbd7989eec08225f3bb704a72103efb7c956e9b"}