{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.28556", "kind": "paper", "url": "https://arxiv.org/abs/2606.28556"}], "authors": ["Maria Xenochristou", "Ashutosh Joshi", "Korosh Vatanparvar", "Mohammad Abuzar Hashemi", "Prasad Kasu", "Deepak Bansal", "Anchal Nema", "Nivedita Wadhwa", "Prashams S Jain", "Rebecca Abraham", "Will Kimbrough", "Dilek Hakkani-Tur", "Wilko Schulz-Mahlendorf"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.28556", "source_url": "https://arxiv.org/abs/2606.28556"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "IMCBench evaluates multimodal LLMs in image-grounded, multi-turn medical conversations, scoring safety, accuracy, and uncertainty use on a 1-5 scale."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.28556", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.28556", "title": "IMCBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.28556", "modality": null, "name": "IMCBench", "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_imcbench_04071d33", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7f7a5b545795dcb952be202f8e6d461d45eab690ee03852d6d7cfad990faba4a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.28556"}, "publisher": null, "released": "2026-06-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.28556", "source_url": "https://arxiv.org/abs/2606.28556"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-28556", "source": "claire_radar", "source_benchmark_id": "2606.28556", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "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/2606.28556", "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": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "2fef12f4c3f66365e3506c1fbdcd60c65c5e5fa36c7811ad5d18a4b1aa727fda", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "IMCBench evaluates multimodal LLMs in image-grounded, multi-turn medical conversations, scoring safety, accuracy, and uncertainty use on a 1-5 scale.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we introduce IMCBench, an image-grounded, multi-turn medical conversation benchmark that pairs real, publicly available clinical images with synthetic patient profiles to simulate realistic patient-clinician interactions."}, "familyId": "bmf_420ea5d66c7d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_imcbench_04071d33", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.28556", "paper": "https://arxiv.org/abs/2606.28556", "pdf": "https://arxiv.org/pdf/2606.28556", "project": null, "report": "https://arxiv.org/abs/2606.28556"}, "metrics": [], "motivation": "Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging.", "name": "IMCBench", "oneLine": "IMCBench evaluates multimodal LLMs in image-grounded, multi-turn medical conversations, scoring safety, accuracy, and uncertainty use on a 1-5 scale.", "paperTitle": "IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": "Accepted at ECML PKDD 2026. 22 pages, 2 figures", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.28556", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ECML PKDD 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-26", "source": {"authors": ["Maria Xenochristou", "Ashutosh Joshi", "Korosh Vatanparvar", "Mohammad Abuzar Hashemi", "Prasad Kasu", "Deepak Bansal", "Anchal Nema", "Nivedita Wadhwa", "Prashams S Jain", "Rebecca Abraham", "Will Kimbrough", "Dilek Hakkani-Tur", "and Wilko Schulz-Mahlendorf"], "categories": ["cs.AI"], "id": "2606.28556", "title": "IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations", "type": "arxiv", "url": "https://arxiv.org/abs/2606.28556"}, "sourceUpdatedAt": "2026-06-26T19:18:16Z", "topics": ["Multimodal"], "venueAttempts": [{"decisionRaw": "Accepted at ECML PKDD 2026. 22 pages, 2 figures", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted at ECML PKDD 2026. 22 pages, 2 figures", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.28556"}], "reviewStatus": "accepted", "venueName": "ECML PKDD 2026"}], "whyItMatters": "Addresses the gap in medical AI benchmarks by combining clinical images with multi-turn dialogue, enabling assessment of diagnostic accuracy alongside patient safety and uncertainty management."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
