{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2BQLA5OBNZDNOFOY7W3OVEH64P","short_pith_number":"pith:2BQLA5OB","schema_version":"1.0","canonical_sha256":"d060b075c16e46d715d8fdb6ea90fee3c4aae6f60c36c82dac8cfc8ff867eb81","source":{"kind":"arxiv","id":"2410.21970","version":1},"attestation_state":"computed","paper":{"title":"Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ante Wang, Baosong Yang, Jialong Tang, Jiawei Yu, Jinsong Su, Junfeng Yao, Kaidi Jia, Suhang Wu","submitted_at":"2024-10-29T11:53:19Z","abstract_excerpt":"RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has received limited research focus. In this work, we propose \\textit{Futurepedia}, a carefully crafted benchmark containing parallel texts across eight representative languages. We evaluate six multilingual RALMs using our benchmark to explore the challenges of multilingual RALMs. Experimental results reveal linguistic inequalities: 1) high-resource languages stan"},"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":"2410.21970","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T11:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"5bb6ee6861f6d0c1427658f97289a6bc68beeae2cb9f35eaa1b931536ac8ddf2","abstract_canon_sha256":"4f9fda896a36a92ca9d1ed73c0c73aae1ba54a69c81a3ffb44db548b9e04b320"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:02.366994Z","signature_b64":"oXpYefCACIfz/glf+muV92aaRWn78GqQXkPaVnsTfgDCmm7F94TzyxvBAXm88GX+7cMBPd+nPhTf4NteENtfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d060b075c16e46d715d8fdb6ea90fee3c4aae6f60c36c82dac8cfc8ff867eb81","last_reissued_at":"2026-07-05T09:28:02.366500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:02.366500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ante Wang, Baosong Yang, Jialong Tang, Jiawei Yu, Jinsong Su, Junfeng Yao, Kaidi Jia, Suhang Wu","submitted_at":"2024-10-29T11:53:19Z","abstract_excerpt":"RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has received limited research focus. In this work, we propose \\textit{Futurepedia}, a carefully crafted benchmark containing parallel texts across eight representative languages. We evaluate six multilingual RALMs using our benchmark to explore the challenges of multilingual RALMs. Experimental results reveal linguistic inequalities: 1) high-resource languages stan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21970","kind":"arxiv","version":1},"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/2410.21970/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":"2410.21970","created_at":"2026-07-05T09:28:02.366563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21970v1","created_at":"2026-07-05T09:28:02.366563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21970","created_at":"2026-07-05T09:28:02.366563+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BQLA5OBNZDN","created_at":"2026-07-05T09:28:02.366563+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BQLA5OBNZDNOFOY","created_at":"2026-07-05T09:28:02.366563+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BQLA5OB","created_at":"2026-07-05T09:28:02.366563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19668","citing_title":"Code-Switching Reveals Language Anchoring in Multilingual LLMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25182","citing_title":"CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P","json":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P.json","graph_json":"https://pith.science/api/pith-number/2BQLA5OBNZDNOFOY7W3OVEH64P/graph.json","events_json":"https://pith.science/api/pith-number/2BQLA5OBNZDNOFOY7W3OVEH64P/events.json","paper":"https://pith.science/paper/2BQLA5OB"},"agent_actions":{"view_html":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P","download_json":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P.json","view_paper":"https://pith.science/paper/2BQLA5OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21970&json=true","fetch_graph":"https://pith.science/api/pith-number/2BQLA5OBNZDNOFOY7W3OVEH64P/graph.json","fetch_events":"https://pith.science/api/pith-number/2BQLA5OBNZDNOFOY7W3OVEH64P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P/action/storage_attestation","attest_author":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P/action/author_attestation","sign_citation":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P/action/citation_signature","submit_replication":"https://pith.science/pith/2BQLA5OBNZDNOFOY7W3OVEH64P/action/replication_record"}},"created_at":"2026-07-05T09:28:02.366563+00:00","updated_at":"2026-07-05T09:28:02.366563+00:00"}