{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7KWU5REXFHBUO565BLIJJYPR6D","short_pith_number":"pith:7KWU5REX","schema_version":"1.0","canonical_sha256":"faad4ec49729c34777dd0ad094e1f1f0f25d4a5cea1665b5b868328c734b4a93","source":{"kind":"arxiv","id":"2407.05502","version":3},"attestation_state":"computed","paper":{"title":"Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Kenton Murray, Nikhil Sharma, Ziang Xiao","submitted_at":"2024-07-07T21:26:36Z","abstract_excerpt":"Although the multilingual capability of LLMs offers new opportunities to overcome the language barrier, do these capabilities translate into real-life scenarios where linguistic divide and knowledge conflicts between multilingual sources are known occurrences? In this paper, we studied LLM's linguistic preference in a cross-language RAG-based information search setting. We found that LLMs displayed systemic bias towards information in the same language as the query language in both document retrieval and answer generation. Furthermore, in scenarios where no information is in the language of 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":"2407.05502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-07T21:26:36Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"b34057c65370c54a50bfdd1b65fdc4ffb3cf80a78a20bcf3261513bff6d5f29f","abstract_canon_sha256":"fac7d1c6a6f4a252b18ae200eb1c483b3bc72786a14691b8d94b2ec5940263b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:43.063789Z","signature_b64":"bl16390fU/yqHo767DjKJPfthzu7XPc8YkX2X9m9rcxT0iMgt4+o9KjZYvnmBIaPyrVtJYwQpMQbFf9HcuRvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faad4ec49729c34777dd0ad094e1f1f0f25d4a5cea1665b5b868328c734b4a93","last_reissued_at":"2026-07-05T11:26:43.063254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:43.063254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Kenton Murray, Nikhil Sharma, Ziang Xiao","submitted_at":"2024-07-07T21:26:36Z","abstract_excerpt":"Although the multilingual capability of LLMs offers new opportunities to overcome the language barrier, do these capabilities translate into real-life scenarios where linguistic divide and knowledge conflicts between multilingual sources are known occurrences? In this paper, we studied LLM's linguistic preference in a cross-language RAG-based information search setting. We found that LLMs displayed systemic bias towards information in the same language as the query language in both document retrieval and answer generation. Furthermore, in scenarios where no information is in the language of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05502","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/2407.05502/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":"2407.05502","created_at":"2026-07-05T11:26:43.063323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05502v3","created_at":"2026-07-05T11:26:43.063323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05502","created_at":"2026-07-05T11:26:43.063323+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KWU5REXFHBU","created_at":"2026-07-05T11:26:43.063323+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KWU5REXFHBUO565","created_at":"2026-07-05T11:26:43.063323+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KWU5REX","created_at":"2026-07-05T11:26:43.063323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D","json":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D.json","graph_json":"https://pith.science/api/pith-number/7KWU5REXFHBUO565BLIJJYPR6D/graph.json","events_json":"https://pith.science/api/pith-number/7KWU5REXFHBUO565BLIJJYPR6D/events.json","paper":"https://pith.science/paper/7KWU5REX"},"agent_actions":{"view_html":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D","download_json":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D.json","view_paper":"https://pith.science/paper/7KWU5REX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05502&json=true","fetch_graph":"https://pith.science/api/pith-number/7KWU5REXFHBUO565BLIJJYPR6D/graph.json","fetch_events":"https://pith.science/api/pith-number/7KWU5REXFHBUO565BLIJJYPR6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D/action/storage_attestation","attest_author":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D/action/author_attestation","sign_citation":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D/action/citation_signature","submit_replication":"https://pith.science/pith/7KWU5REXFHBUO565BLIJJYPR6D/action/replication_record"}},"created_at":"2026-07-05T11:26:43.063323+00:00","updated_at":"2026-07-05T11:26:43.063323+00:00"}