{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.13931", "kind": "paper", "url": "https://arxiv.org/abs/2606.13931"}, {"id": "gh:skylenage-ai/dlawbench", "kind": "repo", "url": "https://github.com/SKYLENAGE-AI/DLawBench"}], "authors": ["Li Zhang", "Yuzhen Shi", "Yiran Hu", "Jingwen Zhang", "Wenbo Lv", "Yubo Ma", "Wei Wang", "Rongyao Shi", "Yuanyang Qiu", "Xinran Xu", "Yuemeng Qi", "Linlin Miao", "Jaromir Savelka", "Yun Liu", "Kevin Ashley", "Bing Zhao", "Hu Wei", "Lin Qu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.13931", "source_url": "https://arxiv.org/abs/2606.13931"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "DLawBench evaluates multi-turn legal consultation in Chinese and U.S. law across four client personas. It scores LLMs on information gathering, legal reasoning, and claim support using 461 cases, 5,532 paired fact entries, inquiry and issue rubrics, and a public leaderboard."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.13931", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.13931", "title": "DLawBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.13931", "modality": null, "name": "DLawBench", "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_dlawbench_4866c9b4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5ec548cfa1f8c9b872de677d725b2275c8817d7c285e749179a0ca702036c01b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.13931"}, "publisher": null, "released": "2026-06-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.13931", "source_url": "https://arxiv.org/abs/2606.13931"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-13931", "source": "claire_radar", "source_benchmark_id": "2606.13931", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/SKYLENAGE-AI/DLawBench", "githubScope": "benchmark_repo", "githubStars": 4, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.13931", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "2c69f1f9a9969aa88bb2f102fa252169159f7fd5b0cc104ee8b1b1d068085f0e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DLawBench evaluates multi-turn legal consultation in Chinese and U.S. law across four client personas. It scores LLMs on information gathering, legal reasoning, and claim support using 461 cases, 5,532 paired fact entries, inquiry and issue rubrics, and a public leaderboard.", "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", "public artifact URL"], "snippet": "To fill this gap, we introduce DLawBench, a diagnostic benchmark for real-world legal consultation."}, "familyId": "bmf_48d9ddc30394", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/SKYLENAGE-AI/DLawBench", "url": "https://github.com/SKYLENAGE-AI/DLawBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/SKYLENAGE-AI/DLawBench", "url": "https://huggingface.co/papers/2606.13931"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/SKYLENAGE-AI/DLawBench", "url": "https://arxiv.org/abs/2606.13931"}], "scope": "benchmark_repo", "url": "https://github.com/SKYLENAGE-AI/DLawBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_dlawbench_4866c9b4", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/SKYLENAGE-AI/DLawBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.13931", "paper": "https://arxiv.org/abs/2606.13931", "pdf": "https://arxiv.org/pdf/2606.13931", "project": null, "report": "https://arxiv.org/abs/2606.13931"}, "metrics": [], "motivation": "Lawyer-client consultation is a critical starting point for legal services.", "name": "DLawBench", "oneLine": "DLawBench evaluates multi-turn legal consultation in Chinese and U.S. law across four client personas. It scores LLMs on information gathering, legal reasoning, and claim support using 461 cases, 5,532 paired fact entries, inquiry and issue rubrics, and a public leaderboard.", "paperTitle": "DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.13931", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "SKYLENAGE-AI", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/SKYLENAGE-AI/DLawBench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-11", "source": {"authors": ["Li Zhang", "Yuzhen Shi", "Yiran Hu", "Jingwen Zhang", "Wenbo Lv", "Yubo Ma", "Wei Wang", "Rongyao Shi", "Yuanyang Qiu", "Xinran Xu", "Yuemeng Qi", "Linlin Miao", "Jaromir Savelka", "Yun Liu", "Kevin Ashley", "Bing Zhao", "Hu Wei", "and Lin Qu"], "categories": ["cs.CL"], "id": "2606.13931", "title": "DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultation", "type": "arxiv", "url": "https://arxiv.org/abs/2606.13931"}, "sourceUpdatedAt": "2026-06-11T21:50:44Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Existing legal benchmarks assume complete fact patterns, overlooking the interactive elicitation needed in real consultations. DLawBench provides a diagnostic evaluation of LLM capability in legal consultation, revealing performance gaps and failure modes that inform development of models for legal assistance."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
