{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24200", "kind": "paper", "url": "https://arxiv.org/abs/2606.24200"}], "authors": ["Junhyeok Lee", "Han Jang", "Hyeonjin Goh", "Kyu Sung Choi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24200", "source_url": "https://arxiv.org/abs/2606.24200"}, "categories": ["Biology & Drug Discovery", "Information retrieval", "Language & Knowledge", "cs.CL"], "description": {"en": "MMed-Bench-IR evaluates multilingual medical information retrieval across 6 languages with three tasks: cross-lingual QA retrieval, concept discrimination, and evidence retrieval for RAG."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24200", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24200", "title": "MMed-Bench-IR"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Seoul National University", "Seoul National University Hospital"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.24200", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.24200", "source_url": "https://openalex.org/W7165758349"}, "key": "claire-radar:2606.24200", "modality": null, "name": "MMed-Bench-IR", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_mmed-bench-ir_04b38f2d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a44ef1da4186393639a3da6035b1e78bc4bd62270f94ae5c7c90b6dbfe2f736f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24200"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24200", "source_url": "https://arxiv.org/abs/2606.24200"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24200", "source": "claire_radar", "source_benchmark_id": "2606.24200", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Biology & Drug Discovery"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.24200", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Information retrieval"], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "1eccf7d331acf480dc1cb1010e929f438b076b6eb13cac6834138aa764c5ad35", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MMed-Bench-IR evaluates multilingual medical information retrieval across 6 languages with three tasks: cross-lingual QA retrieval, concept discrimination, and evidence retrieval for RAG.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce MMed-Bench-IR, a benchmark designed to disentangle these axes across 6 languages and three structurally heterogeneous tasks: (1) cross-lingual medical QA retrieval with 6,127 queries grounded in the Unified Medical Language System (UMLS), (2) concept discrimination over 4,975 confusion sets at three difficulty tiers, and (3) multilingual evidence retrieval for RAG with 2,040 quality-assured queries."}, "familyId": "bmf_00f594160510", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_mmed-bench-ir_04b38f2d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.24200", "paper": "https://arxiv.org/abs/2606.24200", "pdf": "https://arxiv.org/pdf/2606.24200", "project": null, "report": "https://arxiv.org/abs/2606.24200"}, "metrics": [], "motivation": "Retrieval-augmented generation (RAG) in clinical settings increasingly requires multilingual retrieval against predominantly English evidence corpora.", "name": "MMed-Bench-IR", "oneLine": "MMed-Bench-IR evaluates multilingual medical information retrieval across 6 languages with three tasks: cross-lingual QA retrieval, concept discrimination, and evidence retrieval for RAG.", "paperTitle": "MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.24200", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Junhyeok Lee", "Han Jang", "Hyeonjin Goh", "Kyu Sung Choi"], "categories": ["cs.CL", "cs.AI", "cs.IR"], "id": "2606.24200", "title": "MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24200"}, "sourceUpdatedAt": "2026-06-23T06:41:13Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Uncovers severe cross-lingual failures in biomedical encoders that English-only benchmarks miss, highlighting the need for multilingual capability measurement in clinical RAG."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
