{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DYH4MW726ZT73NENHVNILCEUHJ","short_pith_number":"pith:DYH4MW72","schema_version":"1.0","canonical_sha256":"1e0fc65bfaf667fdb48d3d5a8588943a764eb1f1ea1cc94ea61f4476bbd99c6e","source":{"kind":"arxiv","id":"2503.02776","version":1},"attestation_state":"computed","paper":{"title":"Implicit Bias in LLMs: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Luyang Li, Xinru Lin","submitted_at":"2025-03-04T16:49:37Z","abstract_excerpt":"Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who consciously strive for impartiality yet still harbor implicit bias. The unconscious and automatic nature of implicit bias makes it particularly challenging to study. This paper provides a comprehensive review of the existing literature on implicit bias in LLMs. We begin by introducing key concepts, theories and methods related to implicit bias in psychology,"},"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":"2503.02776","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T16:49:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21caa0bff509f1857eba4c457aafc3c6e79ff6466e79e081a2162d4abe4a4250","abstract_canon_sha256":"ce4ae87777548c3fa3545a51a2a5540cf96140453b255e44165e382ac172f647"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:13.666442Z","signature_b64":"YfsNfzVewJ9h1nX/QOdSj2RSTm9rW7vgNux8VXwsoXx2aS5oqe+dSRnvVMpt02YQuC8t7pbJgGKKRQcI8AY0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e0fc65bfaf667fdb48d3d5a8588943a764eb1f1ea1cc94ea61f4476bbd99c6e","last_reissued_at":"2026-07-05T10:24:13.665897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:13.665897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Bias in LLMs: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Luyang Li, Xinru Lin","submitted_at":"2025-03-04T16:49:37Z","abstract_excerpt":"Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who consciously strive for impartiality yet still harbor implicit bias. The unconscious and automatic nature of implicit bias makes it particularly challenging to study. This paper provides a comprehensive review of the existing literature on implicit bias in LLMs. We begin by introducing key concepts, theories and methods related to implicit bias in psychology,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02776","kind":"arxiv","version":1},"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/2503.02776/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":"2503.02776","created_at":"2026-07-05T10:24:13.665953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02776v1","created_at":"2026-07-05T10:24:13.665953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02776","created_at":"2026-07-05T10:24:13.665953+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYH4MW726ZT7","created_at":"2026-07-05T10:24:13.665953+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYH4MW726ZT73NEN","created_at":"2026-07-05T10:24:13.665953+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYH4MW72","created_at":"2026-07-05T10:24:13.665953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25380","citing_title":"A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ","json":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ.json","graph_json":"https://pith.science/api/pith-number/DYH4MW726ZT73NENHVNILCEUHJ/graph.json","events_json":"https://pith.science/api/pith-number/DYH4MW726ZT73NENHVNILCEUHJ/events.json","paper":"https://pith.science/paper/DYH4MW72"},"agent_actions":{"view_html":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ","download_json":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ.json","view_paper":"https://pith.science/paper/DYH4MW72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02776&json=true","fetch_graph":"https://pith.science/api/pith-number/DYH4MW726ZT73NENHVNILCEUHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DYH4MW726ZT73NENHVNILCEUHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ/action/storage_attestation","attest_author":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ/action/author_attestation","sign_citation":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ/action/citation_signature","submit_replication":"https://pith.science/pith/DYH4MW726ZT73NENHVNILCEUHJ/action/replication_record"}},"created_at":"2026-07-05T10:24:13.665953+00:00","updated_at":"2026-07-05T10:24:13.665953+00:00"}