{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JWGPNU354KXCEDWSZLVCDE5IMR","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":"07ea86e724df754a3b758f1263d660b446960c17e27f4e1a4c9d2b8aab5d768d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-14T12:51:38Z","title_canon_sha256":"f6acd2cfb03fe13e33fc335d22599cd853aa1f1057429cd819c1da5eb7de94d2"},"schema_version":"1.0","source":{"id":"2310.09573","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09573","created_at":"2026-07-05T07:01:08Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09573v1","created_at":"2026-07-05T07:01:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09573","created_at":"2026-07-05T07:01:08Z"},{"alias_kind":"pith_short_12","alias_value":"JWGPNU354KXC","created_at":"2026-07-05T07:01:08Z"},{"alias_kind":"pith_short_16","alias_value":"JWGPNU354KXCEDWS","created_at":"2026-07-05T07:01:08Z"},{"alias_kind":"pith_short_8","alias_value":"JWGPNU35","created_at":"2026-07-05T07:01:08Z"}],"graph_snapshots":[{"event_id":"sha256:fb4f522c9a480cf8b5a2199e11b62879e5cdaa5d4407b712bec3b99fbdab2478","target":"graph","created_at":"2026-07-05T07:01:08Z","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/2310.09573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and decoding-based. However, the former is often resource-intensive, while the latter relies on additional components and potentially compromises the generation fluency. In this paper, we propose a more lightweight approach that enables the PLM itself to achieve \"self-detoxification\". Our method is built upon the observation that prepending a negative steering prompt can effe","authors_text":"Chak Tou Leong, Jian Wang, Jiashuo Wang, Wenjie Li, Yi Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-14T12:51:38Z","title":"Self-Detoxifying Language Models via Toxification Reversal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09573","kind":"arxiv","version":1},"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":"sha256:0a687185dcb145cf220f57aa322be40f2def433b6b0e59d9f421c306c89a140f","target":"record","created_at":"2026-07-05T07:01:08Z","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":"07ea86e724df754a3b758f1263d660b446960c17e27f4e1a4c9d2b8aab5d768d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-14T12:51:38Z","title_canon_sha256":"f6acd2cfb03fe13e33fc335d22599cd853aa1f1057429cd819c1da5eb7de94d2"},"schema_version":"1.0","source":{"id":"2310.09573","kind":"arxiv","version":1}},"canonical_sha256":"4d8cf6d37de2ae220ed2caea2193a8645a52343e7e7407128ed0bb4897abe02b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d8cf6d37de2ae220ed2caea2193a8645a52343e7e7407128ed0bb4897abe02b","first_computed_at":"2026-07-05T07:01:08.077601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:08.077601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PGYYY7rtAXbQ8jMv7VpAsY7VYa4zraaAPrSEkjgOYXa1sA7Xj9Ni2vYGb/cMXgxw+x7NKnEilRHVMKEGjis2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:08.078106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09573","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a687185dcb145cf220f57aa322be40f2def433b6b0e59d9f421c306c89a140f","sha256:fb4f522c9a480cf8b5a2199e11b62879e5cdaa5d4407b712bec3b99fbdab2478"],"state_sha256":"b03a4b5c2462c54af791008b990fc7b3b9e74595219bb2868f962a16dc6baa2c"}