{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.11584", "kind": "paper", "url": "https://arxiv.org/abs/2608.11584"}], "authors": ["Huiqi Miao", "Xinbao Sun", "Bo Wang", "Fanyu Meng", "Lijun Mei", "Na Wu", "Di Jin", "Chao Deng", "Junlan Feng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.11584", "source_url": "https://arxiv.org/abs/2608.11584"}, "categories": ["Factuality", "General AI", "Information retrieval", "Robustness", "Safety & Trustworthiness", "cs.AI"], "description": {"en": "The benchmark evaluates LLM instruction adherence and robustness in enterprise retrieval scenarios, using 983 expert-validated samples across six domains, simulating retrieval noise, knowledge gaps, and factual conflicts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.11584", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.11584", "title": "EnterpriseRAG"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Jiuquan Iron & Steel (China)", "China Mobile (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.11584", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.11584", "source_url": "https://openalex.org/W7202391783"}, "key": "claire-radar:2608.11584", "modality": null, "name": "EnterpriseRAG", "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_enterpriserag_49e3b609", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "df2b8f8af8bef30173dbe6df642027cddd46e1774c028dd1bd8a4afff624e28d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.11584"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.11584", "source_url": "https://arxiv.org/abs/2608.11584"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-11584", "source": "claire_radar", "source_benchmark_id": "2608.11584", "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/2608.11584", "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", "Robustness", "Factuality"], "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": "0d95abb771fcce5a6b9fac9c7f67ebbd1c0e79f449ded04813552f41eefac32a", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The benchmark evaluates LLM instruction adherence and robustness in enterprise retrieval scenarios, using 983 expert-validated samples across six domains, simulating retrieval noise, knowledge gaps, and factual conflicts.", "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 EnterpriseRAG, a benchmark of 983 expert-validated samples across six domains that systematically simulates three failure modes absent from prior work: retrieval noise, knowledge gaps, and factual conflicts, coupled with complex instructions."}, "familyId": "bmf_11382aad9957", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_enterpriserag_49e3b609", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.11584", "paper": "https://arxiv.org/abs/2608.11584", "pdf": "https://arxiv.org/pdf/2608.11584", "project": null, "report": "https://arxiv.org/abs/2608.11584"}, "metrics": [], "motivation": "Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.8% of responses meet all requirements simultaneously, revealing a 57-point orchestration gap.", "name": "EnterpriseRAG", "oneLine": "The benchmark evaluates LLM instruction adherence and robustness in enterprise retrieval scenarios, using 983 expert-validated samples across six domains, simulating retrieval noise, knowledge gaps, and factual conflicts.", "paperTitle": "EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.11584", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"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": "2026-08-12", "source": {"authors": ["Huiqi Miao", "Xinbao Sun", "Bo Wang", "Fanyu Meng", "Lijun Mei", "Na Wu", "Di Jin", "Chao Deng", "Junlan Feng"], "categories": ["cs.AI"], "id": "2608.11584", "title": "EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval", "type": "arxiv", "url": "https://arxiv.org/abs/2608.11584"}, "sourceUpdatedAt": "2026-08-12T02:51:04Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing RAG benchmarks assume clean retrieval and simple queries, failing to capture production conditions. This benchmark addresses the gap by measuring holistic compliance under non-ideal conditions, informing deployment decisions for enterprise-scale RAG systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
