{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I6PDZFARVVGR5YNLAQ2Y3FZTBO","short_pith_number":"pith:I6PDZFAR","schema_version":"1.0","canonical_sha256":"479e3c9411ad4d1ee1ab04358d97330bb567ded26d107bffbd07e009fc121404","source":{"kind":"arxiv","id":"2410.17578","version":2},"attestation_state":"computed","paper":{"title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongkeun Yoon, Guijin Son, Jaume Prats-Cristi\\`a, Javier Aula-Blasco, Juyoung Suk, Luc\\'ia Tormo-Ba\\~nuelos, Mano Aslan, Seungone Kim, Shayekh Bin Islam, Vu Trong Kim","submitted_at":"2024-10-23T06:04:55Z","abstract_excerpt":"As Large Language Models (LLMs) are now capable of producing fluent and coherent content in languages other than English, it is not imperative to precisely evaluate these non-English outputs. However, when assessing the outputs from mutlilingual LLMs, prior works often employed LLM based evaluators that excel at assessing English outputs, without a thorough examination of whether these evaluators could effectively assess non-English text as well. Moreover, existing benchmarks to test evaluator LLMs (referred to as \"meta-evaluation benchmarks\") are mostly English-centric. To bridge this gap and"},"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":"2410.17578","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T06:04:55Z","cross_cats_sorted":[],"title_canon_sha256":"282db59af1c616b5cf67501062a09148369a1934988db603f2f08c9f9eec036b","abstract_canon_sha256":"0000ce4906a24f728a48e783b1ed965cc703c493dd4a051b5121bed480d59b07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:16.413807Z","signature_b64":"rBH/0wIZ9N3bZDPZSbLe7/xo2MoBNgsJs7GzWZCmfMoIRFVT1NOSnqAGddxYj0jtfgRQ13DzyvNXBFtkQ+mXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"479e3c9411ad4d1ee1ab04358d97330bb567ded26d107bffbd07e009fc121404","last_reissued_at":"2026-07-05T10:41:16.413213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:16.413213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongkeun Yoon, Guijin Son, Jaume Prats-Cristi\\`a, Javier Aula-Blasco, Juyoung Suk, Luc\\'ia Tormo-Ba\\~nuelos, Mano Aslan, Seungone Kim, Shayekh Bin Islam, Vu Trong Kim","submitted_at":"2024-10-23T06:04:55Z","abstract_excerpt":"As Large Language Models (LLMs) are now capable of producing fluent and coherent content in languages other than English, it is not imperative to precisely evaluate these non-English outputs. However, when assessing the outputs from mutlilingual LLMs, prior works often employed LLM based evaluators that excel at assessing English outputs, without a thorough examination of whether these evaluators could effectively assess non-English text as well. Moreover, existing benchmarks to test evaluator LLMs (referred to as \"meta-evaluation benchmarks\") are mostly English-centric. To bridge this gap and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17578","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/2410.17578/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":"2410.17578","created_at":"2026-07-05T10:41:16.413292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17578v2","created_at":"2026-07-05T10:41:16.413292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17578","created_at":"2026-07-05T10:41:16.413292+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6PDZFARVVGR","created_at":"2026-07-05T10:41:16.413292+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6PDZFARVVGR5YNL","created_at":"2026-07-05T10:41:16.413292+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6PDZFAR","created_at":"2026-07-05T10:41:16.413292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02235","citing_title":"Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languages","ref_index":195,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26955","citing_title":"JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07874","citing_title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":209,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04532","citing_title":"Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19144","citing_title":"ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO","json":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO.json","graph_json":"https://pith.science/api/pith-number/I6PDZFARVVGR5YNLAQ2Y3FZTBO/graph.json","events_json":"https://pith.science/api/pith-number/I6PDZFARVVGR5YNLAQ2Y3FZTBO/events.json","paper":"https://pith.science/paper/I6PDZFAR"},"agent_actions":{"view_html":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO","download_json":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO.json","view_paper":"https://pith.science/paper/I6PDZFAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17578&json=true","fetch_graph":"https://pith.science/api/pith-number/I6PDZFARVVGR5YNLAQ2Y3FZTBO/graph.json","fetch_events":"https://pith.science/api/pith-number/I6PDZFARVVGR5YNLAQ2Y3FZTBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO/action/storage_attestation","attest_author":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO/action/author_attestation","sign_citation":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO/action/citation_signature","submit_replication":"https://pith.science/pith/I6PDZFARVVGR5YNLAQ2Y3FZTBO/action/replication_record"}},"created_at":"2026-07-05T10:41:16.413292+00:00","updated_at":"2026-07-05T10:41:16.413292+00:00"}