{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J7EO6EA5RY4OBRUFI2ZTFYIKAE","short_pith_number":"pith:J7EO6EA5","schema_version":"1.0","canonical_sha256":"4fc8ef101d8e38e0c68546b332e10a0111e4db40d3f9201fea88679fd4c03b2a","source":{"kind":"arxiv","id":"2403.09073","version":3},"attestation_state":"computed","paper":{"title":"Revealing the Parallel Multilingual Learning within Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Li, Chenglong Wang, Chunliang Zhang, Jingbo Zhu, Kai Song, Peinan Feng, Tongran Liu, Tong Xiao, Yongyu Mu, Yuzhang Wu, Zhiquan Cao","submitted_at":"2024-03-14T03:33:46Z","abstract_excerpt":"In this study, we reveal an in-context learning (ICL) capability of multilingual large language models (LLMs): by translating the input to several languages, we provide Parallel Input in Multiple Languages (PiM) to LLMs, which significantly enhances their comprehension abilities. To test this capability, we design extensive experiments encompassing 8 typical datasets, 7 languages and 8 state-of-the-art multilingual LLMs. Experimental results show that (1) incorporating more languages help PiM surpass the conventional ICL further; (2) even combining with the translations that are inferior to ba"},"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":"2403.09073","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T03:33:46Z","cross_cats_sorted":[],"title_canon_sha256":"2e372295450ccf1d02b8d0bd4b0ad510c7c2ff3b1d0212b524ab09a975239246","abstract_canon_sha256":"63324c157c3fb9ddc5c8d44e7ac3a90b75eb75dc964503f1356552a65fcb9048"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:23.292372Z","signature_b64":"q7oMotvDctFOy4kJm5WRYcWq8Y5ORW/ipCxCCQMfqkZZb2hBSMPPIcx1Y6f5GHRLaOjITC0/enaLQvhcacinDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fc8ef101d8e38e0c68546b332e10a0111e4db40d3f9201fea88679fd4c03b2a","last_reissued_at":"2026-07-05T11:14:23.291702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:23.291702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revealing the Parallel Multilingual Learning within Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Li, Chenglong Wang, Chunliang Zhang, Jingbo Zhu, Kai Song, Peinan Feng, Tongran Liu, Tong Xiao, Yongyu Mu, Yuzhang Wu, Zhiquan Cao","submitted_at":"2024-03-14T03:33:46Z","abstract_excerpt":"In this study, we reveal an in-context learning (ICL) capability of multilingual large language models (LLMs): by translating the input to several languages, we provide Parallel Input in Multiple Languages (PiM) to LLMs, which significantly enhances their comprehension abilities. To test this capability, we design extensive experiments encompassing 8 typical datasets, 7 languages and 8 state-of-the-art multilingual LLMs. Experimental results show that (1) incorporating more languages help PiM surpass the conventional ICL further; (2) even combining with the translations that are inferior to ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09073","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/2403.09073/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":"2403.09073","created_at":"2026-07-05T11:14:23.291783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09073v3","created_at":"2026-07-05T11:14:23.291783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09073","created_at":"2026-07-05T11:14:23.291783+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7EO6EA5RY4O","created_at":"2026-07-05T11:14:23.291783+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7EO6EA5RY4OBRUF","created_at":"2026-07-05T11:14:23.291783+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7EO6EA5","created_at":"2026-07-05T11:14:23.291783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07086","citing_title":"Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE","json":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE.json","graph_json":"https://pith.science/api/pith-number/J7EO6EA5RY4OBRUFI2ZTFYIKAE/graph.json","events_json":"https://pith.science/api/pith-number/J7EO6EA5RY4OBRUFI2ZTFYIKAE/events.json","paper":"https://pith.science/paper/J7EO6EA5"},"agent_actions":{"view_html":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE","download_json":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE.json","view_paper":"https://pith.science/paper/J7EO6EA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09073&json=true","fetch_graph":"https://pith.science/api/pith-number/J7EO6EA5RY4OBRUFI2ZTFYIKAE/graph.json","fetch_events":"https://pith.science/api/pith-number/J7EO6EA5RY4OBRUFI2ZTFYIKAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE/action/storage_attestation","attest_author":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE/action/author_attestation","sign_citation":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE/action/citation_signature","submit_replication":"https://pith.science/pith/J7EO6EA5RY4OBRUFI2ZTFYIKAE/action/replication_record"}},"created_at":"2026-07-05T11:14:23.291783+00:00","updated_at":"2026-07-05T11:14:23.291783+00:00"}