{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QCZ3XI7LEB4EX5QEWMFBNSSIBZ","short_pith_number":"pith:QCZ3XI7L","schema_version":"1.0","canonical_sha256":"80b3bba3eb20784bf604b30a16ca480e5fa11ae943355dcc42b9fc1741fbd06b","source":{"kind":"arxiv","id":"2312.11361","version":3},"attestation_state":"computed","paper":{"title":"\"Knowing When You Don't Know\": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Boxing Chen, David Alfonso-Hermelo, Ehsan Kamalloo, Jimmy Lin, Luiz Bonifacio, Mehdi Rezagholizadeh, Nandan Thakur, Odunayo Ogundepo, Qun Liu, Xiaoguang Li, Xinyu Zhang","submitted_at":"2023-12-18T17:18:04Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. However, prior work lacks a comprehensive evaluation of different language families, making it challenging to evaluate LLM robustness against errors in external retrieved knowledge. To overcome this, we establish NoMIRACL, a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. NoMIRACL includes both a non-relevant and a relevant subset. Queries in the non-relevant subset contain passages judg"},"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":"2312.11361","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T17:18:04Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1c14cc63655085c2f8868eb7bf032646f9e4270128b45c6cd918c8255d073d0b","abstract_canon_sha256":"06b2eb1db0c05b89a5cd6e0f4584e28a167973083401037353d1805bb5eb8160"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:27.626035Z","signature_b64":"4agyj66wOiwa541DDoQATBkOcvgE/9mX/go+0XPmyU38MX9QXMKF3rPAlHCYtPhPdLIZ3tNNMjXMCWt77zuLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80b3bba3eb20784bf604b30a16ca480e5fa11ae943355dcc42b9fc1741fbd06b","last_reissued_at":"2026-07-05T09:33:27.625567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:27.625567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Knowing When You Don't Know\": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Boxing Chen, David Alfonso-Hermelo, Ehsan Kamalloo, Jimmy Lin, Luiz Bonifacio, Mehdi Rezagholizadeh, Nandan Thakur, Odunayo Ogundepo, Qun Liu, Xiaoguang Li, Xinyu Zhang","submitted_at":"2023-12-18T17:18:04Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. However, prior work lacks a comprehensive evaluation of different language families, making it challenging to evaluate LLM robustness against errors in external retrieved knowledge. To overcome this, we establish NoMIRACL, a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. NoMIRACL includes both a non-relevant and a relevant subset. Queries in the non-relevant subset contain passages judg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11361","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/2312.11361/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":"2312.11361","created_at":"2026-07-05T09:33:27.625622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11361v3","created_at":"2026-07-05T09:33:27.625622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11361","created_at":"2026-07-05T09:33:27.625622+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCZ3XI7LEB4E","created_at":"2026-07-05T09:33:27.625622+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCZ3XI7LEB4EX5QE","created_at":"2026-07-05T09:33:27.625622+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCZ3XI7L","created_at":"2026-07-05T09:33:27.625622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12138","citing_title":"Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ","json":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ.json","graph_json":"https://pith.science/api/pith-number/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/graph.json","events_json":"https://pith.science/api/pith-number/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/events.json","paper":"https://pith.science/paper/QCZ3XI7L"},"agent_actions":{"view_html":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ","download_json":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ.json","view_paper":"https://pith.science/paper/QCZ3XI7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11361&json=true","fetch_graph":"https://pith.science/api/pith-number/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/action/storage_attestation","attest_author":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/action/author_attestation","sign_citation":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/action/citation_signature","submit_replication":"https://pith.science/pith/QCZ3XI7LEB4EX5QEWMFBNSSIBZ/action/replication_record"}},"created_at":"2026-07-05T09:33:27.625622+00:00","updated_at":"2026-07-05T09:33:27.625622+00:00"}