{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZESMADIX2B6HHZKRTRG3B7HFVF","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":"1ace5dc97e46ede0f0e90f2a668d6b760d848a8bf42034c8cd07c30a9adad3ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","title_canon_sha256":"7c08b767bb235f8bb25439a2516d945b097792223b9886c583cb839908e4be66"},"schema_version":"1.0","source":{"id":"2310.11079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11079","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11079v1","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11079","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZESMADIX2B6H","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZESMADIX2B6HHZKR","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZESMADIX","created_at":"2026-07-05T07:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:a8867a99aeade339c1d9cd16b178f60d52d4e73b46db926e7d9a0d8718e4b34d","target":"graph","created_at":"2026-07-05T07:01:50Z","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/2310.11079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots encode the potential biases while retaining disparities that can harm humans during interactions. The traditional biases investigation methods often rely on human-written test cases. However, these test cases are usually expensive and limited. In this work, we propose a first-of-its-kind method that automatically generates test cases to detect LLMs' potential gender bias. We apply our method to three well-known LLMs ","authors_text":"Cheng-Chu Cheng, Hsuan Su, Hua Farn, Hung-yi Lee, Saurav Sahay, Shachi H Kumar, Shang-Tse Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11079","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":"sha256:5e3c04c2b1398b7453ad5eb50263c5ba6dbdfeceb84c649eacd9417161123235","target":"record","created_at":"2026-07-05T07:01:50Z","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":"1ace5dc97e46ede0f0e90f2a668d6b760d848a8bf42034c8cd07c30a9adad3ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","title_canon_sha256":"7c08b767bb235f8bb25439a2516d945b097792223b9886c583cb839908e4be66"},"schema_version":"1.0","source":{"id":"2310.11079","kind":"arxiv","version":1}},"canonical_sha256":"c924c00d17d07c73e5519c4db0fce5a96613a40d0cbe4065411c6d2905730638","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c924c00d17d07c73e5519c4db0fce5a96613a40d0cbe4065411c6d2905730638","first_computed_at":"2026-07-05T07:01:50.052707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:50.052707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+0y1lHHyEF9jq+BM2ai/lSJ992TjQwKHQxP4jq12IUOxFZiJ0Qn4E1h4g+r2EuT1MjvpEu/BnE7MoS0A0LyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:50.053184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e3c04c2b1398b7453ad5eb50263c5ba6dbdfeceb84c649eacd9417161123235","sha256:a8867a99aeade339c1d9cd16b178f60d52d4e73b46db926e7d9a0d8718e4b34d"],"state_sha256":"a73077dc39d9cb0722232ee2bfdebe19bb76fe173c8528343b58f774a38b30a7"}