{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RZMTYGMOZUSLIDABHH2I3H73W2","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":"f33188da23c4c7ad8893e3a7c5c95df5a291303494fa96c6df9753d3c1da541a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-18T16:27:04Z","title_canon_sha256":"7ebe9ba113a47315ed478c7980b68950fad4342f5697f3b9481afd68be4a7ea5"},"schema_version":"1.0","source":{"id":"2308.09662","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09662","created_at":"2026-07-05T06:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09662v3","created_at":"2026-07-05T06:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09662","created_at":"2026-07-05T06:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"RZMTYGMOZUSL","created_at":"2026-07-05T06:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"RZMTYGMOZUSLIDAB","created_at":"2026-07-05T06:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"RZMTYGMO","created_at":"2026-07-05T06:46:07Z"}],"graph_snapshots":[{"event_id":"sha256:c5f5890ad68cf5c113b75fe4c5883109eaaeb7a4b983ec4e839ddfe1289ab17e","target":"graph","created_at":"2026-07-05T06:46:07Z","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/2308.09662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of LLMs producing harmful outputs increases, making them unfit for scalable deployment for the public. In this work, we propose a new safety evaluation benchmark RED-EVAL that carries out red-teaming. We show that even widely deployed models are susceptible to the Chain of Utterances-based (CoU) prompting, jailbreaking closed source LLM-based systems such as GP","authors_text":"Rishabh Bhardwaj, Soujanya Poria","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-18T16:27:04Z","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09662","kind":"arxiv","version":3},"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":"sha256:8bf558a7ddbdf63964efe85a6057041e60fc893a0d12689656b457ea46801e42","target":"record","created_at":"2026-07-05T06:46:07Z","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":"f33188da23c4c7ad8893e3a7c5c95df5a291303494fa96c6df9753d3c1da541a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-18T16:27:04Z","title_canon_sha256":"7ebe9ba113a47315ed478c7980b68950fad4342f5697f3b9481afd68be4a7ea5"},"schema_version":"1.0","source":{"id":"2308.09662","kind":"arxiv","version":3}},"canonical_sha256":"8e593c198ecd24b40c0139f48d9ffbb693c89c79b3e3492317e562f4a59c656b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e593c198ecd24b40c0139f48d9ffbb693c89c79b3e3492317e562f4a59c656b","first_computed_at":"2026-07-05T06:46:07.487628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:07.487628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kb4b4pzjo3Ca4g9TUqAjbawLliGlaLQElw/KsmrEtz02BjsICkFQPwtXhwl035br9OSMz7v1LxumMoeYSjctBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:07.488050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09662","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bf558a7ddbdf63964efe85a6057041e60fc893a0d12689656b457ea46801e42","sha256:c5f5890ad68cf5c113b75fe4c5883109eaaeb7a4b983ec4e839ddfe1289ab17e"],"state_sha256":"4153afddfe3b22ddcf0c8345ed639ea85748a543291b33c37c01db8b408ce603"}