{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6RWH4ONZ4GWNLEH26OZBDE4II2","short_pith_number":"pith:6RWH4ONZ","schema_version":"1.0","canonical_sha256":"f46c7e39b9e1acd590faf3b2119388469cd857a1c5dfa6d823ad4272639498b8","source":{"kind":"arxiv","id":"2410.14012","version":2},"attestation_state":"computed","paper":{"title":"LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Haewon Jeong, Iain Weissburg, Sathvika Anand, Sharon Levy","submitted_at":"2024-10-17T20:27:44Z","abstract_excerpt":"With the increasing adoption of large language models (LLMs) in education, concerns about inherent biases in these models have gained prominence. We evaluate LLMs for bias in the personalized educational setting, specifically focusing on the models' roles as \"teachers.\" We reveal significant biases in how models generate and select educational content tailored to different demographic groups, including race, ethnicity, sex, gender, disability status, income, and national origin. We introduce and apply two bias score metrics--Mean Absolute Bias (MAB) and Maximum Difference Bias (MDB)--to analyz"},"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":"2410.14012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T20:27:44Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"05cd9cdfd46c77701c113cbe37bfc3f731cd49300e223fefdbfc837ba302ee3c","abstract_canon_sha256":"378f2bc42b8dfe74b477b6c020073894cacff76381b4b37e181e419486996523"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:26.528789Z","signature_b64":"mBe69/bXhTBa2vWU6p29XghifGfEi1roxlOYxDQ0n0sEfHaFuoy9pBKgHmj5PdNc4gAeR5qz+lip3HXa/gC4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f46c7e39b9e1acd590faf3b2119388469cd857a1c5dfa6d823ad4272639498b8","last_reissued_at":"2026-07-05T10:11:26.528259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:26.528259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Haewon Jeong, Iain Weissburg, Sathvika Anand, Sharon Levy","submitted_at":"2024-10-17T20:27:44Z","abstract_excerpt":"With the increasing adoption of large language models (LLMs) in education, concerns about inherent biases in these models have gained prominence. We evaluate LLMs for bias in the personalized educational setting, specifically focusing on the models' roles as \"teachers.\" We reveal significant biases in how models generate and select educational content tailored to different demographic groups, including race, ethnicity, sex, gender, disability status, income, and national origin. We introduce and apply two bias score metrics--Mean Absolute Bias (MAB) and Maximum Difference Bias (MDB)--to analyz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14012","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/2410.14012/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":"2410.14012","created_at":"2026-07-05T10:11:26.528323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14012v2","created_at":"2026-07-05T10:11:26.528323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14012","created_at":"2026-07-05T10:11:26.528323+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RWH4ONZ4GWN","created_at":"2026-07-05T10:11:26.528323+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RWH4ONZ4GWNLEH2","created_at":"2026-07-05T10:11:26.528323+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RWH4ONZ","created_at":"2026-07-05T10:11:26.528323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21296","citing_title":"Discriminatory Compliance: How LLMs Answer Queries from Protected Groups","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15340","citing_title":"Restoration, Exploration and Transformation: How Youth Engage Character.AI Chatbots for Feels, Fun and Finding themselves","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2","json":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2.json","graph_json":"https://pith.science/api/pith-number/6RWH4ONZ4GWNLEH26OZBDE4II2/graph.json","events_json":"https://pith.science/api/pith-number/6RWH4ONZ4GWNLEH26OZBDE4II2/events.json","paper":"https://pith.science/paper/6RWH4ONZ"},"agent_actions":{"view_html":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2","download_json":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2.json","view_paper":"https://pith.science/paper/6RWH4ONZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14012&json=true","fetch_graph":"https://pith.science/api/pith-number/6RWH4ONZ4GWNLEH26OZBDE4II2/graph.json","fetch_events":"https://pith.science/api/pith-number/6RWH4ONZ4GWNLEH26OZBDE4II2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2/action/storage_attestation","attest_author":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2/action/author_attestation","sign_citation":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2/action/citation_signature","submit_replication":"https://pith.science/pith/6RWH4ONZ4GWNLEH26OZBDE4II2/action/replication_record"}},"created_at":"2026-07-05T10:11:26.528323+00:00","updated_at":"2026-07-05T10:11:26.528323+00:00"}