{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MPHLBBGPDP2HCBBQ5MM5K2RAK4","short_pith_number":"pith:MPHLBBGP","schema_version":"1.0","canonical_sha256":"63ceb084cf1bf4710430eb19d56a20573dac4b74d0f42de7b2652e757706d7d6","source":{"kind":"arxiv","id":"2409.16430","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC"],"primary_cat":"cs.CL","authors_text":"Rajesh Ranjan, Shailja Gupta, Surya Narayan Singh","submitted_at":"2024-09-24T19:50:38Z","abstract_excerpt":"Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has brought to light significant concerns regarding biases embedded within these models. This paper presents a comprehensive survey of biases in LLMs, aiming to provide an extensive review of the types, sources, impacts, and mitigation strategies related to these biases. We systematically categorize biases into several dimensions. Our survey synthesizes current rese"},"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":"2409.16430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T19:50:38Z","cross_cats_sorted":["cs.AI","cs.CY","cs.HC"],"title_canon_sha256":"8894cdaee8d8e23e2f9502d0110a846e4f477f5319cf5eb972226fbef7813fcf","abstract_canon_sha256":"6b77eba05d596b17c843271731e06ee2322f2b6ed3f8d7589e5b53e604d1c1e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:33.514563Z","signature_b64":"hMPGfuPJAPZUMTKwuocMuG70KcUjvTaGLWjSnhHxryE6uAyqr6Q/xKBngoGsl5bWt2+SYvjUZgZM8Gg2BZg9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63ceb084cf1bf4710430eb19d56a20573dac4b74d0f42de7b2652e757706d7d6","last_reissued_at":"2026-07-05T09:11:33.514069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:33.514069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC"],"primary_cat":"cs.CL","authors_text":"Rajesh Ranjan, Shailja Gupta, Surya Narayan Singh","submitted_at":"2024-09-24T19:50:38Z","abstract_excerpt":"Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has brought to light significant concerns regarding biases embedded within these models. This paper presents a comprehensive survey of biases in LLMs, aiming to provide an extensive review of the types, sources, impacts, and mitigation strategies related to these biases. We systematically categorize biases into several dimensions. Our survey synthesizes current rese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16430","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/2409.16430/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":"2409.16430","created_at":"2026-07-05T09:11:33.514126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16430v1","created_at":"2026-07-05T09:11:33.514126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16430","created_at":"2026-07-05T09:11:33.514126+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPHLBBGPDP2H","created_at":"2026-07-05T09:11:33.514126+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPHLBBGPDP2HCBBQ","created_at":"2026-07-05T09:11:33.514126+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPHLBBGP","created_at":"2026-07-05T09:11:33.514126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08311","citing_title":"Curation of a Cardiology Interface Terminology for Highlighting Electronic Health Records using Machine Learning","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15790","citing_title":"Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19768","citing_title":"Saying More Than They Know: A Framework for Quantifying Epistemic-Rhetorical Miscalibration in Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18038","citing_title":"First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11663","citing_title":"Why Do Large Language Models Generate Harmful Content?","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11589","citing_title":"MLLM-as-a-Judge Exhibits Model Preference Bias","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4","json":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4.json","graph_json":"https://pith.science/api/pith-number/MPHLBBGPDP2HCBBQ5MM5K2RAK4/graph.json","events_json":"https://pith.science/api/pith-number/MPHLBBGPDP2HCBBQ5MM5K2RAK4/events.json","paper":"https://pith.science/paper/MPHLBBGP"},"agent_actions":{"view_html":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4","download_json":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4.json","view_paper":"https://pith.science/paper/MPHLBBGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16430&json=true","fetch_graph":"https://pith.science/api/pith-number/MPHLBBGPDP2HCBBQ5MM5K2RAK4/graph.json","fetch_events":"https://pith.science/api/pith-number/MPHLBBGPDP2HCBBQ5MM5K2RAK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4/action/storage_attestation","attest_author":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4/action/author_attestation","sign_citation":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4/action/citation_signature","submit_replication":"https://pith.science/pith/MPHLBBGPDP2HCBBQ5MM5K2RAK4/action/replication_record"}},"created_at":"2026-07-05T09:11:33.514126+00:00","updated_at":"2026-07-05T09:11:33.514126+00:00"}