{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SUGVL3GN5S2NXGWPQQSEKAKUZR","short_pith_number":"pith:SUGVL3GN","schema_version":"1.0","canonical_sha256":"950d55eccdecb4db9acf8424450154cc7a00b9f1bb009db65361eea7f6709470","source":{"kind":"arxiv","id":"2404.08699","version":3},"attestation_state":"computed","paper":{"title":"PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Agiza, Mohamed Mostagir, Sherief Reda","submitted_at":"2024-04-10T16:30:09Z","abstract_excerpt":"In an era where language models are increasingly integrated into decision-making and communication, understanding the biases within Large Language Models (LLMs) becomes imperative, especially when these models are applied in the economic and political domains. This work investigates the impact of fine-tuning and data selection on economic and political biases in LLMs. In this context, we introduce PoliTune, a fine-tuning methodology to explore the systematic aspects of aligning LLMs with specific ideologies, mindful of the biases that arise from their extensive training on diverse datasets. Di"},"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":"2404.08699","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T16:30:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"17b1aabc0028faebd2cb645dd486946744600f174ed657a174125c9c80b1d3a7","abstract_canon_sha256":"5a2e8578b06e47ba8823c7c76cc72cdd9d3335a2296e99335de230277ef44e7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:33.038269Z","signature_b64":"rSww2gmcUuhvJ6PRFYQkJE8+y9+12iKOzmRz7kn/esHlRx1nNyMoOAq9gVDx51/xEd78K2TPLg7t5eTFdxjkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"950d55eccdecb4db9acf8424450154cc7a00b9f1bb009db65361eea7f6709470","last_reissued_at":"2026-07-05T08:49:33.037724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:33.037724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Agiza, Mohamed Mostagir, Sherief Reda","submitted_at":"2024-04-10T16:30:09Z","abstract_excerpt":"In an era where language models are increasingly integrated into decision-making and communication, understanding the biases within Large Language Models (LLMs) becomes imperative, especially when these models are applied in the economic and political domains. This work investigates the impact of fine-tuning and data selection on economic and political biases in LLMs. In this context, we introduce PoliTune, a fine-tuning methodology to explore the systematic aspects of aligning LLMs with specific ideologies, mindful of the biases that arise from their extensive training on diverse datasets. Di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08699","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/2404.08699/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":"2404.08699","created_at":"2026-07-05T08:49:33.037781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08699v3","created_at":"2026-07-05T08:49:33.037781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08699","created_at":"2026-07-05T08:49:33.037781+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUGVL3GN5S2N","created_at":"2026-07-05T08:49:33.037781+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUGVL3GN5S2NXGWP","created_at":"2026-07-05T08:49:33.037781+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUGVL3GN","created_at":"2026-07-05T08:49:33.037781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.19463","citing_title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16113","citing_title":"DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR","json":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR.json","graph_json":"https://pith.science/api/pith-number/SUGVL3GN5S2NXGWPQQSEKAKUZR/graph.json","events_json":"https://pith.science/api/pith-number/SUGVL3GN5S2NXGWPQQSEKAKUZR/events.json","paper":"https://pith.science/paper/SUGVL3GN"},"agent_actions":{"view_html":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR","download_json":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR.json","view_paper":"https://pith.science/paper/SUGVL3GN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08699&json=true","fetch_graph":"https://pith.science/api/pith-number/SUGVL3GN5S2NXGWPQQSEKAKUZR/graph.json","fetch_events":"https://pith.science/api/pith-number/SUGVL3GN5S2NXGWPQQSEKAKUZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR/action/storage_attestation","attest_author":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR/action/author_attestation","sign_citation":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR/action/citation_signature","submit_replication":"https://pith.science/pith/SUGVL3GN5S2NXGWPQQSEKAKUZR/action/replication_record"}},"created_at":"2026-07-05T08:49:33.037781+00:00","updated_at":"2026-07-05T08:49:33.037781+00:00"}