{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ULBKL7V6B2FTPVT2GVBY37GJLQ","short_pith_number":"pith:ULBKL7V6","schema_version":"1.0","canonical_sha256":"a2c2a5febe0e8b37d67a35438dfcc95c3850f4c279f1a2bdd74653580ddb7228","source":{"kind":"arxiv","id":"2302.02463","version":3},"attestation_state":"computed","paper":{"title":"Nationality Bias in Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pranav Narayanan Venkit, Ruchi Panchanadikar, Sanjana Gautam, Shomir Wilson, Ting-Hao 'Kenneth' Huang","submitted_at":"2023-02-05T19:15:33Z","abstract_excerpt":"Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore th"},"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":"2302.02463","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-05T19:15:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea10abc153baa772b465a6b97cdf1f4c0c9f9b15489919eb9b3e3e66c1751993","abstract_canon_sha256":"5d50965c70a035c6dc8c8e8a0c4342272cce43daaff37e03cb50cf52f2e6af38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:52.209196Z","signature_b64":"Un1Ur0l2OkvY7LxD6fzjnTLQ69gTonBCVzqyu94ku7mdFa/4aV6LtzAa1uOZH66y2QVO8YkWklrovXdEaSGfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2c2a5febe0e8b37d67a35438dfcc95c3850f4c279f1a2bdd74653580ddb7228","last_reissued_at":"2026-07-05T05:41:52.208789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:52.208789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nationality Bias in Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pranav Narayanan Venkit, Ruchi Panchanadikar, Sanjana Gautam, Shomir Wilson, Ting-Hao 'Kenneth' Huang","submitted_at":"2023-02-05T19:15:33Z","abstract_excerpt":"Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02463","kind":"arxiv","version":3},"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/2302.02463/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":"2302.02463","created_at":"2026-07-05T05:41:52.208845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02463v3","created_at":"2026-07-05T05:41:52.208845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02463","created_at":"2026-07-05T05:41:52.208845+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULBKL7V6B2FT","created_at":"2026-07-05T05:41:52.208845+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULBKL7V6B2FTPVT2","created_at":"2026-07-05T05:41:52.208845+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULBKL7V6","created_at":"2026-07-05T05:41:52.208845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28044","citing_title":"A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs","ref_index":237,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06649","citing_title":"Measuring Stereotype and Deviation Biases in Large Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06816","citing_title":"How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02834","citing_title":"Clustering Discourses: Racial Biases in Short Stories about Women Generated by Large Language Models","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ","json":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ.json","graph_json":"https://pith.science/api/pith-number/ULBKL7V6B2FTPVT2GVBY37GJLQ/graph.json","events_json":"https://pith.science/api/pith-number/ULBKL7V6B2FTPVT2GVBY37GJLQ/events.json","paper":"https://pith.science/paper/ULBKL7V6"},"agent_actions":{"view_html":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ","download_json":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ.json","view_paper":"https://pith.science/paper/ULBKL7V6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02463&json=true","fetch_graph":"https://pith.science/api/pith-number/ULBKL7V6B2FTPVT2GVBY37GJLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ULBKL7V6B2FTPVT2GVBY37GJLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/action/storage_attestation","attest_author":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/action/author_attestation","sign_citation":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/action/citation_signature","submit_replication":"https://pith.science/pith/ULBKL7V6B2FTPVT2GVBY37GJLQ/action/replication_record"}},"created_at":"2026-07-05T05:41:52.208845+00:00","updated_at":"2026-07-05T05:41:52.208845+00:00"}