{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y77GEETYI24EBXNGU4X6MT5JAM","short_pith_number":"pith:Y77GEETY","schema_version":"1.0","canonical_sha256":"c7fe62127846b840dda6a72fe64fa90318ac4e756cc1739090357913133779c7","source":{"kind":"arxiv","id":"2404.10508","version":5},"attestation_state":"computed","paper":{"title":"White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Kai-Wei Chang, Yixin Wan","submitted_at":"2024-04-16T12:27:54Z","abstract_excerpt":"Social biases can manifest in language agency. However, very limited research has investigated such biases in Large Language Model (LLM)-generated content. In addition, previous works often rely on string-matching techniques to identify agentic and communal words within texts, falling short of accurately classifying language agency. We introduce the Language Agency Bias Evaluation (LABE) benchmark, which comprehensively evaluates biases in LLMs by analyzing agency levels attributed to different demographic groups in model generations. LABE tests for gender, racial, and intersectional language "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.10508","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-16T12:27:54Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"06c62aeadbcd44be956dbd71d0abe8523e8712a5beeb943b22335e84aeba70b6","abstract_canon_sha256":"b2bbb6e6c6779d77ee96d3529937e95b219d4c6bc0487f0e6b91dc3fbb5b68a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:08.922611Z","signature_b64":"dpH0TYTw83dcdu1Kj1TjfdkEFVeZFtxvoglEeLARsblqm/0o40rEjWcXyOB8ymrtQzdxsQ4PYzs8vTmGE5GXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7fe62127846b840dda6a72fe64fa90318ac4e756cc1739090357913133779c7","last_reissued_at":"2026-07-05T11:13:08.922018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:08.922018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Kai-Wei Chang, Yixin Wan","submitted_at":"2024-04-16T12:27:54Z","abstract_excerpt":"Social biases can manifest in language agency. However, very limited research has investigated such biases in Large Language Model (LLM)-generated content. In addition, previous works often rely on string-matching techniques to identify agentic and communal words within texts, falling short of accurately classifying language agency. We introduce the Language Agency Bias Evaluation (LABE) benchmark, which comprehensively evaluates biases in LLMs by analyzing agency levels attributed to different demographic groups in model generations. LABE tests for gender, racial, and intersectional language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10508","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.10508/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.10508","created_at":"2026-07-05T11:13:08.922084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10508v5","created_at":"2026-07-05T11:13:08.922084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10508","created_at":"2026-07-05T11:13:08.922084+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y77GEETYI24E","created_at":"2026-07-05T11:13:08.922084+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y77GEETYI24EBXNG","created_at":"2026-07-05T11:13:08.922084+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y77GEETY","created_at":"2026-07-05T11:13:08.922084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.18466","citing_title":"Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05189","citing_title":"Small Changes, Big Impact: Demographic Bias in LLM-Based Hiring Through Subtle Sociocultural Markers in Anonymised Resumes","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM","json":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM.json","graph_json":"https://pith.science/api/pith-number/Y77GEETYI24EBXNGU4X6MT5JAM/graph.json","events_json":"https://pith.science/api/pith-number/Y77GEETYI24EBXNGU4X6MT5JAM/events.json","paper":"https://pith.science/paper/Y77GEETY"},"agent_actions":{"view_html":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM","download_json":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM.json","view_paper":"https://pith.science/paper/Y77GEETY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10508&json=true","fetch_graph":"https://pith.science/api/pith-number/Y77GEETYI24EBXNGU4X6MT5JAM/graph.json","fetch_events":"https://pith.science/api/pith-number/Y77GEETYI24EBXNGU4X6MT5JAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM/action/storage_attestation","attest_author":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM/action/author_attestation","sign_citation":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM/action/citation_signature","submit_replication":"https://pith.science/pith/Y77GEETYI24EBXNGU4X6MT5JAM/action/replication_record"}},"created_at":"2026-07-05T11:13:08.922084+00:00","updated_at":"2026-07-05T11:13:08.922084+00:00"}