{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WKTOUXEXEZIELVDIBY7QR5B5DY","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":"159b13004aa1885b1b06a712b20744d7fd3c29205d2377c8370da289111eaf9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T15:51:24Z","title_canon_sha256":"f498b1829b1043710f604b2cacf238ad8a44397bca798c4280a3c386ff7a17fb"},"schema_version":"1.0","source":{"id":"2410.22153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22153","created_at":"2026-07-05T09:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22153v1","created_at":"2026-07-05T09:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22153","created_at":"2026-07-05T09:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"WKTOUXEXEZIE","created_at":"2026-07-05T09:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"WKTOUXEXEZIELVDI","created_at":"2026-07-05T09:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"WKTOUXEX","created_at":"2026-07-05T09:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:339f3a7cf04da1b9be049d9ece3e0475ead87781422732700515d961401ef5ff","target":"graph","created_at":"2026-07-05T09:28:04Z","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/2410.22153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiveness in handling multilingual toxic inputs remains unclear. In this work, we introduce a comprehensive multilingual test suite, spanning seven datasets and over ten languages, to benchmark the performance of state-of-the-art guardrails. We also investigates the resilience of guardrails against recent jailbreaking techniques, and assess the impact of in-context safety policies an","authors_text":"Dan Roth, Insup Lee, Soham Dan, Yahan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T15:51:24Z","title":"Benchmarking LLM Guardrails in Handling Multilingual Toxicity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22153","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:dbddd8bbeadde74ac2b7a2b47846993466a3cea427baf00445e9163a10b31229","target":"record","created_at":"2026-07-05T09:28:04Z","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":"159b13004aa1885b1b06a712b20744d7fd3c29205d2377c8370da289111eaf9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T15:51:24Z","title_canon_sha256":"f498b1829b1043710f604b2cacf238ad8a44397bca798c4280a3c386ff7a17fb"},"schema_version":"1.0","source":{"id":"2410.22153","kind":"arxiv","version":1}},"canonical_sha256":"b2a6ea5c97265045d4680e3f08f43d1e026e9c03bdc8a1ac07138e83d1621731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2a6ea5c97265045d4680e3f08f43d1e026e9c03bdc8a1ac07138e83d1621731","first_computed_at":"2026-07-05T09:28:04.836364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:04.836364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kksC1ybaatXROFlqnGCi1+mCvF7sHMZ373Y/k2+5gA1LQZePg2A0Y+kfzJOQRBSifp2FkSm0t/cTIQxK7MS4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:04.836850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbddd8bbeadde74ac2b7a2b47846993466a3cea427baf00445e9163a10b31229","sha256:339f3a7cf04da1b9be049d9ece3e0475ead87781422732700515d961401ef5ff"],"state_sha256":"7b3fce08d04d6e1ca766c27c48807f8577829b78055bf8184fba29df08c534b2"}