{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MGW3OIR7OBM7Y7BZJAWKH4LMEW","short_pith_number":"pith:MGW3OIR7","schema_version":"1.0","canonical_sha256":"61adb7223f7059fc7c39482ca3f16c25898f463e756cf30c06f7a790ad26a764","source":{"kind":"arxiv","id":"2308.10149","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Fairness in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mengnan Du, Rui Song, Xin Wang, Yingji Li, Ying Wang","submitted_at":"2023-08-20T03:30:22Z","abstract_excerpt":"Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms. In this paper, we provide a comprehensive review of related research on fairness in LLMs. Considering the influence of parameter magnitude and training paradigm on research strategy, we divide existing fairness research into oriented to medium-sized LLMs under pre-training and fin"},"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":"2308.10149","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-20T03:30:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a760557488b5641b3441b9daf3c87dcd05ecf800cdd943c052317479b47a8b9e","abstract_canon_sha256":"922f6103765349f43e46966b8969d2216e7dac5deaf513e0269849a1cc4615f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:44.512864Z","signature_b64":"LHIL5BArQsq92192Jif/XebERW1jx85iJRT5tCxW/xM3S9A3NvYgwQ5Ojr20jLCadaDhi107yi6AceU5eWVqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61adb7223f7059fc7c39482ca3f16c25898f463e756cf30c06f7a790ad26a764","last_reissued_at":"2026-07-05T07:47:44.512362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:44.512362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Fairness in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mengnan Du, Rui Song, Xin Wang, Yingji Li, Ying Wang","submitted_at":"2023-08-20T03:30:22Z","abstract_excerpt":"Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms. In this paper, we provide a comprehensive review of related research on fairness in LLMs. Considering the influence of parameter magnitude and training paradigm on research strategy, we divide existing fairness research into oriented to medium-sized LLMs under pre-training and fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10149","kind":"arxiv","version":2},"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/2308.10149/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":"2308.10149","created_at":"2026-07-05T07:47:44.512426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10149v2","created_at":"2026-07-05T07:47:44.512426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10149","created_at":"2026-07-05T07:47:44.512426+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGW3OIR7OBM7","created_at":"2026-07-05T07:47:44.512426+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGW3OIR7OBM7Y7BZ","created_at":"2026-07-05T07:47:44.512426+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGW3OIR7","created_at":"2026-07-05T07:47:44.512426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18656","citing_title":"The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10126","citing_title":"Pareto-Guided Teacher Alignment for Fair Personalized Text Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30152","citing_title":"Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28098","citing_title":"Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2411.00585","citing_title":"Fairness Testing of Large Language Models in Role-Playing","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19463","citing_title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26851","citing_title":"Resume-ing Control: (Mis)Perceptions of Agency Around GenAI Use in Recruiting Workflows","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20677","citing_title":"Intersectional Fairness in Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05555","citing_title":"SCOPE: A Dataset of Stereotyped Prompts for Counterfactual Fairness Assessment of LLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16780","citing_title":"FairNVT: Improving Fairness via Noise Injection in Vision Transformers","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW","json":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW.json","graph_json":"https://pith.science/api/pith-number/MGW3OIR7OBM7Y7BZJAWKH4LMEW/graph.json","events_json":"https://pith.science/api/pith-number/MGW3OIR7OBM7Y7BZJAWKH4LMEW/events.json","paper":"https://pith.science/paper/MGW3OIR7"},"agent_actions":{"view_html":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW","download_json":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW.json","view_paper":"https://pith.science/paper/MGW3OIR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10149&json=true","fetch_graph":"https://pith.science/api/pith-number/MGW3OIR7OBM7Y7BZJAWKH4LMEW/graph.json","fetch_events":"https://pith.science/api/pith-number/MGW3OIR7OBM7Y7BZJAWKH4LMEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW/action/storage_attestation","attest_author":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW/action/author_attestation","sign_citation":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW/action/citation_signature","submit_replication":"https://pith.science/pith/MGW3OIR7OBM7Y7BZJAWKH4LMEW/action/replication_record"}},"created_at":"2026-07-05T07:47:44.512426+00:00","updated_at":"2026-07-05T07:47:44.512426+00:00"}