{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.11758", "kind": "paper", "url": "https://arxiv.org/abs/2609.11758"}], "authors": ["Adithiyan Rajan Indira Saravanan", "Kathleen C. Fraser"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.11758", "source_url": "https://arxiv.org/abs/2609.11758"}, "categories": ["General AI", "Information retrieval", "Safety", "Safety & Trustworthiness"], "description": {"en": "Measurement of the safety impact of retrieval augmentation on LLM outputs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.11758", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.11758", "title": "RAG-Safety-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.11758", "modality": null, "name": "RAG-Safety-Bench", "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": "false", "origin_record_id": "bm_rag-safety-bench_6807be74", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d36a1f9a7a29a359b261fc52b4e8825c4e8f9f7b0f7938bc51302d6769ed6757", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-14T00:43:53.625753Z", "source_url": "https://arxiv.org/abs/2609.11758"}, "publisher": null, "released": "2026-09-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.11758", "source_url": "https://arxiv.org/abs/2609.11758"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-11758", "source": "claire_radar", "source_benchmark_id": "2609.11758", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Safety & Trustworthiness", "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/2609.11758", "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"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Substantial artifact or community evidence is needed to drive initial attention.", "score": 0}, "capabilities": ["Information retrieval"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-14T00:43:53.625753Z", "inputHash": "c9ca96905856ebc60107acc327f9def144266f5a9a2396a4db8a1bf49c50bf95", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Insufficient evidence on benchmark implementation, scoring rules, or public reuse path.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-14T00:43:53.625753Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Measurement of the safety impact of retrieval augmentation on LLM outputs.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce RAG-Safety-Bench, a benchmark to measure the safety impact of RAG on LLM models."}, "familyId": "bmf_99ac9c2bbb9c", "firstSeenAt": "2026-09-11", "heat": null, "id": "bm_rag-safety-bench_6807be74", "indexedAt": "2026-09-11T06:20:12.012226Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.11758", "pdf": "https://arxiv.org/pdf/2609.11758", "project": null, "report": "https://arxiv.org/abs/2609.11758"}, "metrics": [], "motivation": "Allowing large language models (LLMs) to retrieve information from a set of trusted documents can increase reliability and reduce hallucination.", "name": "RAG-Safety-Bench", "oneLine": "Measurement of the safety impact of retrieval augmentation on LLM outputs.", "paperTitle": "RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.11758", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-11T06:20:12.012226Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-10", "source": {"authors": ["Adithiyan Rajan Indira Saravanan and Kathleen C. Fraser"], "categories": ["cs.CL", "cs.IR"], "id": "2609.11758", "title": "RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety", "type": "arxiv", "url": "https://arxiv.org/abs/2609.11758"}, "sourceUpdatedAt": "2026-09-10T16:12:25Z", "topics": ["Safety"], "venueAttempts": [], "whyItMatters": "Addresses the need for reliable safety evaluation in retrieval-augmented language models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
