{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3YUWILYXT7Q4QB5YCCUFIR52QN","short_pith_number":"pith:3YUWILYX","schema_version":"1.0","canonical_sha256":"de29642f179fe1c807b810a85447ba8362313ff0721ba1e6d86e44191e071242","source":{"kind":"arxiv","id":"2410.08928","version":2},"attestation_state":"computed","paper":{"title":"Towards Multilingual LLM Evaluation for European Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Jude, Bernhard Stadler, Fabio Barth, Jasper Schulze Buschhoff, Joachim k\\\"ohler, Johannes Leveling, Klaudia Thellmann, Mehdi Ali, Michael Fromm, Nicolas Flores-Herr, Ren\\'e J\\\"akel","submitted_at":"2024-10-11T15:53:24Z","abstract_excerpt":"The rise of Large Language Models (LLMs) has revolutionized natural language processing across numerous languages and tasks. However, evaluating LLM performance in a consistent and meaningful way across multiple European languages remains challenging, especially due to the scarcity of language-parallel multilingual benchmarks. We introduce a multilingual evaluation approach tailored for European languages. We employ translated versions of five widely-used benchmarks to assess the capabilities of 40 LLMs across 21 European languages. Our contributions include examining the effectiveness of tran"},"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":"2410.08928","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T15:53:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7458c02765060a5070340ff3cec80a510cec9c96029809fe4681930330057cac","abstract_canon_sha256":"1da6ea82542404a748bbeec8cd42f592b95c6ee4ab05852ba71726ab777ab89f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:49.848114Z","signature_b64":"mmsFLCe4fIc+cAp/pINCK6XlHtV3E141+3otndfy+2pFWzKrSjjRtGcJIQsNs2FZyFduDapqqWohJI1JTSxkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de29642f179fe1c807b810a85447ba8362313ff0721ba1e6d86e44191e071242","last_reissued_at":"2026-07-05T09:21:49.847661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:49.847661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Multilingual LLM Evaluation for European Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Jude, Bernhard Stadler, Fabio Barth, Jasper Schulze Buschhoff, Joachim k\\\"ohler, Johannes Leveling, Klaudia Thellmann, Mehdi Ali, Michael Fromm, Nicolas Flores-Herr, Ren\\'e J\\\"akel","submitted_at":"2024-10-11T15:53:24Z","abstract_excerpt":"The rise of Large Language Models (LLMs) has revolutionized natural language processing across numerous languages and tasks. However, evaluating LLM performance in a consistent and meaningful way across multiple European languages remains challenging, especially due to the scarcity of language-parallel multilingual benchmarks. We introduce a multilingual evaluation approach tailored for European languages. We employ translated versions of five widely-used benchmarks to assess the capabilities of 40 LLMs across 21 European languages. Our contributions include examining the effectiveness of tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08928","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/2410.08928/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":"2410.08928","created_at":"2026-07-05T09:21:49.847718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08928v2","created_at":"2026-07-05T09:21:49.847718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08928","created_at":"2026-07-05T09:21:49.847718+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YUWILYXT7Q4","created_at":"2026-07-05T09:21:49.847718+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YUWILYXT7Q4QB5Y","created_at":"2026-07-05T09:21:49.847718+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YUWILYX","created_at":"2026-07-05T09:21:49.847718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13111","citing_title":"M\\\"OVE: A Holistic LLM Benchmark for the German Public Sector","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03773","citing_title":"KletterMix: Climbing Toward High-Quality German Pretraining Data","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01995","citing_title":"CARTE: A Benchmark for Mapping Language Model Knowledge Across France","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10013","citing_title":"Training LLMs on HPC Systems: Best Practices from the OpenGPT-X Project","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN","json":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN.json","graph_json":"https://pith.science/api/pith-number/3YUWILYXT7Q4QB5YCCUFIR52QN/graph.json","events_json":"https://pith.science/api/pith-number/3YUWILYXT7Q4QB5YCCUFIR52QN/events.json","paper":"https://pith.science/paper/3YUWILYX"},"agent_actions":{"view_html":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN","download_json":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN.json","view_paper":"https://pith.science/paper/3YUWILYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08928&json=true","fetch_graph":"https://pith.science/api/pith-number/3YUWILYXT7Q4QB5YCCUFIR52QN/graph.json","fetch_events":"https://pith.science/api/pith-number/3YUWILYXT7Q4QB5YCCUFIR52QN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN/action/storage_attestation","attest_author":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN/action/author_attestation","sign_citation":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN/action/citation_signature","submit_replication":"https://pith.science/pith/3YUWILYXT7Q4QB5YCCUFIR52QN/action/replication_record"}},"created_at":"2026-07-05T09:21:49.847718+00:00","updated_at":"2026-07-05T09:21:49.847718+00:00"}