{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EFXJ3EBL3MQ7I6MCCJFMJE6RNV","short_pith_number":"pith:EFXJ3EBL","schema_version":"1.0","canonical_sha256":"216e9d902bdb21f47982124ac493d16d738b4d765682b82e2e5b16e09e50520d","source":{"kind":"arxiv","id":"2309.07462","version":2},"attestation_state":"computed","paper":{"title":"Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrian de Wynter, Harshita Diddee, Kalika Bali, Mohamed Ahmed, Monojit Choudhury, Rishav Hada, Sunayana Sitaram, Varun Gumma","submitted_at":"2023-09-14T06:41:58Z","abstract_excerpt":"Large Language Models (LLMs) excel in various Natural Language Processing (NLP) tasks, yet their evaluation, particularly in languages beyond the top $20$, remains inadequate due to existing benchmarks and metrics limitations. Employing LLMs as evaluators to rank or score other models' outputs emerges as a viable solution, addressing the constraints tied to human annotators and established benchmarks. In this study, we explore the potential of LLM-based evaluators, specifically GPT-4 in enhancing multilingual evaluation by calibrating them against $20$K human judgments across three text-genera"},"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":"2309.07462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T06:41:58Z","cross_cats_sorted":[],"title_canon_sha256":"6da735c07a08a98c7eeab1f561e1386b64712b678ef4cf2411e34b0069df555e","abstract_canon_sha256":"cf98ad6cae354cd8b408bb1a8a070f196f6642f358c2caa3de622fe3989e3246"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:20.273663Z","signature_b64":"kk6oh/kxIx8MX6wv0ph+JNmXy0TN3owIG7DQdQs4Mvqx0N2mArcNzMZ7bFN38TXjs7+ZKuQ4gWVscv0EFK4OBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"216e9d902bdb21f47982124ac493d16d738b4d765682b82e2e5b16e09e50520d","last_reissued_at":"2026-07-05T07:44:20.273155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:20.273155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrian de Wynter, Harshita Diddee, Kalika Bali, Mohamed Ahmed, Monojit Choudhury, Rishav Hada, Sunayana Sitaram, Varun Gumma","submitted_at":"2023-09-14T06:41:58Z","abstract_excerpt":"Large Language Models (LLMs) excel in various Natural Language Processing (NLP) tasks, yet their evaluation, particularly in languages beyond the top $20$, remains inadequate due to existing benchmarks and metrics limitations. Employing LLMs as evaluators to rank or score other models' outputs emerges as a viable solution, addressing the constraints tied to human annotators and established benchmarks. In this study, we explore the potential of LLM-based evaluators, specifically GPT-4 in enhancing multilingual evaluation by calibrating them against $20$K human judgments across three text-genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07462","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/2309.07462/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":"2309.07462","created_at":"2026-07-05T07:44:20.273213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07462v2","created_at":"2026-07-05T07:44:20.273213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07462","created_at":"2026-07-05T07:44:20.273213+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFXJ3EBL3MQ7","created_at":"2026-07-05T07:44:20.273213+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFXJ3EBL3MQ7I6MC","created_at":"2026-07-05T07:44:20.273213+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFXJ3EBL","created_at":"2026-07-05T07:44:20.273213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV","json":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV.json","graph_json":"https://pith.science/api/pith-number/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/graph.json","events_json":"https://pith.science/api/pith-number/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/events.json","paper":"https://pith.science/paper/EFXJ3EBL"},"agent_actions":{"view_html":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV","download_json":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV.json","view_paper":"https://pith.science/paper/EFXJ3EBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07462&json=true","fetch_graph":"https://pith.science/api/pith-number/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/graph.json","fetch_events":"https://pith.science/api/pith-number/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/action/storage_attestation","attest_author":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/action/author_attestation","sign_citation":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/action/citation_signature","submit_replication":"https://pith.science/pith/EFXJ3EBL3MQ7I6MCCJFMJE6RNV/action/replication_record"}},"created_at":"2026-07-05T07:44:20.273213+00:00","updated_at":"2026-07-05T07:44:20.273213+00:00"}