{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.29427", "kind": "paper", "url": "https://arxiv.org/abs/2605.29427"}], "authors": ["Huaixia Dou", "Jie Zhu", "Minghao Wu", "Shuo Jiang", "Junhui Li", "Lifan Guo", "Feng Chen", "Chi Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.29427", "source_url": "https://arxiv.org/abs/2605.29427"}, "categories": ["Factuality", "Finance", "Vision & 3D", "cs.CL"], "description": {"en": "The evaluation focuses on financial regulatory non-compliance detection in LLM interactions. It involves a benchmark with expert-annotated labels at query and response levels, but the exact task, environment, or scoring setup is not detailed."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.29427", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.29427", "title": "FinGuard-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.29427", "modality": null, "name": "FinGuard-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_finguard-bench_2ed68349", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "c0d39d9307ba8591f85e9d277b404c09c97bd7b5e2612be77c1130f4e5f2ecfe", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.29427"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.29427", "source_url": "https://arxiv.org/abs/2605.29427"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-29427", "source": "claire_radar", "source_benchmark_id": "2605.29427", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Vision & 3D", "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/2605.29427", "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": ["Factuality"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "f5c8732092120b651918c492e57dd0230a19d411da15903312f2e1b3152e919b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The evaluation focuses on financial regulatory non-compliance detection in LLM interactions. It involves a benchmark with expert-annotated labels at query and response levels, but the exact task, environment, or scoring setup is not detailed.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "Instantiating the pipeline on Chinese financial regulations, we release \\textbf{FinGuard-Bench}, to our knowledge the first benchmark for financial regulatory compliance detection, with expert-annotated labels at both the query and response levels."}, "familyId": "bmf_02e6f20cf325", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_finguard-bench_2ed68349", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.29427", "paper": "https://arxiv.org/abs/2605.29427", "pdf": "https://arxiv.org/pdf/2605.29427", "project": null, "report": "https://arxiv.org/abs/2605.29427"}, "metrics": [], "motivation": "As large language models (LLMs) are increasingly deployed in financial services, a single non-compliant interaction can expose institutions to regulatory penalties and direct consumer harm.", "name": "FinGuard-Bench", "oneLine": "The evaluation focuses on financial regulatory non-compliance detection in LLM interactions. It involves a benchmark with expert-annotated labels at query and response levels, but the exact task, environment, or scoring setup is not detailed.", "paperTitle": "FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.29427", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-05-28", "source": {"authors": ["Huaixia Dou", "Jie Zhu", "Minghao Wu", "Shuo Jiang", "Junhui Li", "Lifan Guo", "Feng Chen", "Chi Zhang"], "categories": ["cs.CL"], "id": "2605.29427", "title": "FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions", "type": "arxiv", "url": "https://arxiv.org/abs/2605.29427"}, "sourceUpdatedAt": "2026-05-28T06:20:45Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Assesses LLM compliance with financial regulations, which is critical for preventing regulatory penalties and consumer harm in financial services. The benchmark aims to measure detection capabilities across institution-specific policies."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
