{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2F5IE6KBLOE2C3WX7QCTELFEL5","short_pith_number":"pith:2F5IE6KB","schema_version":"1.0","canonical_sha256":"d17a8279415b89a16ed7fc05322ca45f68e442f561e1398790d2ed34dc5f728c","source":{"kind":"arxiv","id":"2408.09701","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhijit Mishra, Mingda Li, Utkarsh Mujumdar","submitted_at":"2024-08-19T05:11:46Z","abstract_excerpt":"The use of Large Language Models (LLMs) for program code generation has gained substantial attention, but their biases and limitations with non-English prompts challenge global inclusivity. This paper investigates the complexities of multilingual prompt-based code generation. Our evaluations of LLMs, including CODELLAMA and CODEGEMMA, reveal significant disparities in code quality for non-English prompts; we also demonstrate the inadequacy of simple approaches like prompt translation, bootstrapped data augmentation, and fine-tuning. To address this, we propose a zero-shot cross-lingual approac"},"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":"2408.09701","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T05:11:46Z","cross_cats_sorted":[],"title_canon_sha256":"0adff4f6743b468d00e8b2393ceb47773ed7b79e8d50147534acf8ce6fa04bbe","abstract_canon_sha256":"42ae68e305c8097e606b47cde47f683b5ccc69bed3518e065948b8f855e7314f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:01.001885Z","signature_b64":"/jthC8AUkY2nLkDnEVAAICwwX1DdLllkwsNme11VajzOE2gRl+8zmWmwbA7KQWp2vRTfXXp1jl+1IOqV1vt2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17a8279415b89a16ed7fc05322ca45f68e442f561e1398790d2ed34dc5f728c","last_reissued_at":"2026-07-05T11:01:00.999422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:00.999422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhijit Mishra, Mingda Li, Utkarsh Mujumdar","submitted_at":"2024-08-19T05:11:46Z","abstract_excerpt":"The use of Large Language Models (LLMs) for program code generation has gained substantial attention, but their biases and limitations with non-English prompts challenge global inclusivity. This paper investigates the complexities of multilingual prompt-based code generation. Our evaluations of LLMs, including CODELLAMA and CODEGEMMA, reveal significant disparities in code quality for non-English prompts; we also demonstrate the inadequacy of simple approaches like prompt translation, bootstrapped data augmentation, and fine-tuning. To address this, we propose a zero-shot cross-lingual approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09701","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/2408.09701/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":"2408.09701","created_at":"2026-07-05T11:01:01.001330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09701v2","created_at":"2026-07-05T11:01:01.001330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09701","created_at":"2026-07-05T11:01:01.001330+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F5IE6KBLOE2","created_at":"2026-07-05T11:01:01.001330+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F5IE6KBLOE2C3WX","created_at":"2026-07-05T11:01:01.001330+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F5IE6KB","created_at":"2026-07-05T11:01:01.001330+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/2F5IE6KBLOE2C3WX7QCTELFEL5","json":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5.json","graph_json":"https://pith.science/api/pith-number/2F5IE6KBLOE2C3WX7QCTELFEL5/graph.json","events_json":"https://pith.science/api/pith-number/2F5IE6KBLOE2C3WX7QCTELFEL5/events.json","paper":"https://pith.science/paper/2F5IE6KB"},"agent_actions":{"view_html":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5","download_json":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5.json","view_paper":"https://pith.science/paper/2F5IE6KB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09701&json=true","fetch_graph":"https://pith.science/api/pith-number/2F5IE6KBLOE2C3WX7QCTELFEL5/graph.json","fetch_events":"https://pith.science/api/pith-number/2F5IE6KBLOE2C3WX7QCTELFEL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5/action/storage_attestation","attest_author":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5/action/author_attestation","sign_citation":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5/action/citation_signature","submit_replication":"https://pith.science/pith/2F5IE6KBLOE2C3WX7QCTELFEL5/action/replication_record"}},"created_at":"2026-07-05T11:01:01.001330+00:00","updated_at":"2026-07-05T11:01:01.001330+00:00"}