{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C7ZI7TRDGIINO4TC2MZ3RGNTDD","short_pith_number":"pith:C7ZI7TRD","schema_version":"1.0","canonical_sha256":"17f28fce233210d77262d333b899b318c0516667722ebf6468f8bf20c4033fec","source":{"kind":"arxiv","id":"2404.11553","version":3},"attestation_state":"computed","paper":{"title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Payani, Fan Yang, Mengnan Du, Ninghao Liu, Yucheng Shi, Zihao Li, Zirui Liu","submitted_at":"2024-04-17T16:53:16Z","abstract_excerpt":"The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using inte"},"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":"2404.11553","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-17T16:53:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c62c3891f342db6514c769ab937ac99ce4eb2ac703786ac4d8171df24e5bb6aa","abstract_canon_sha256":"e299efe8a4421621d8bb6a11493d2d94841216fd445e18f2ee7f7b7c2a25227e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:29.703555Z","signature_b64":"f1pB6s0X2fzbNqm5nLbwaOTHwOSH7kBCLeJtyZHWUoKz/L8IVZUb1a55pb1nvc+v3zWFHons3ODzPvZPDlT5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17f28fce233210d77262d333b899b318c0516667722ebf6468f8bf20c4033fec","last_reissued_at":"2026-07-05T09:47:29.702998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:29.702998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Payani, Fan Yang, Mengnan Du, Ninghao Liu, Yucheng Shi, Zihao Li, Zirui Liu","submitted_at":"2024-04-17T16:53:16Z","abstract_excerpt":"The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11553","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/2404.11553/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":"2404.11553","created_at":"2026-07-05T09:47:29.703054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11553v3","created_at":"2026-07-05T09:47:29.703054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11553","created_at":"2026-07-05T09:47:29.703054+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7ZI7TRDGIIN","created_at":"2026-07-05T09:47:29.703054+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7ZI7TRDGIINO4TC","created_at":"2026-07-05T09:47:29.703054+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7ZI7TRD","created_at":"2026-07-05T09:47:29.703054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06738","citing_title":"Modular Monolingual Adaptation using Pretrained Language Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00356","citing_title":"How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10590","citing_title":"Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD","json":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD.json","graph_json":"https://pith.science/api/pith-number/C7ZI7TRDGIINO4TC2MZ3RGNTDD/graph.json","events_json":"https://pith.science/api/pith-number/C7ZI7TRDGIINO4TC2MZ3RGNTDD/events.json","paper":"https://pith.science/paper/C7ZI7TRD"},"agent_actions":{"view_html":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD","download_json":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD.json","view_paper":"https://pith.science/paper/C7ZI7TRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11553&json=true","fetch_graph":"https://pith.science/api/pith-number/C7ZI7TRDGIINO4TC2MZ3RGNTDD/graph.json","fetch_events":"https://pith.science/api/pith-number/C7ZI7TRDGIINO4TC2MZ3RGNTDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD/action/storage_attestation","attest_author":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD/action/author_attestation","sign_citation":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD/action/citation_signature","submit_replication":"https://pith.science/pith/C7ZI7TRDGIINO4TC2MZ3RGNTDD/action/replication_record"}},"created_at":"2026-07-05T09:47:29.703054+00:00","updated_at":"2026-07-05T09:47:29.703054+00:00"}