{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.20220", "kind": "paper", "url": "https://arxiv.org/abs/2608.20220"}], "authors": ["Samuel J. Vincent", "Daniel Calloway", "Fangyi Yu", "Andrew M. Bean", "Nabeel Seedat"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.20220", "source_url": "https://arxiv.org/abs/2608.20220"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates whether LLMs recognize legally material missing information in underspecified queries and refrain from premature conclusions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.20220", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.20220", "title": "InsufficiencyBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Thomson Reuters Foundation", "Imperial College London"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.20220", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.20220", "source_url": "https://openalex.org/W7203929186"}, "key": "claire-radar:2608.20220", "modality": null, "name": "InsufficiencyBench", "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": "true", "origin_record_id": "bm_insufficiencybench_debc0b74", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "e1b845fa0fc035d9788a81db22489bbeafe0f8b3c66b7343630d22c661364866", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.20220"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.20220", "source_url": "https://arxiv.org/abs/2608.20220"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-20220", "source": "claire_radar", "source_benchmark_id": "2608.20220", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.20220", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "InsufficiencyBench has substantial expert annotation and an award, but the source lacks an explicit release statement beyond the paper.", "score": 52}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "13a0a40fa2d3268541a631cae2cfb4a97e3598bc757836b5f61be30d7e931e5e", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce InsufficiencyBench, the first legal benchmark targeting query-side insufficiency", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is formally named, has 202 attorney-annotated items with an 8-category taxonomy and evaluation metrics, and received recognition at an AI4Law workshop.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates whether LLMs recognize legally material missing information in underspecified queries and refrain from premature conclusions.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce InsufficiencyBench, the first legal benchmark targeting query-side insufficiency: whether a model recognizes when a query lacks legally material information, identifies what is missing, and refrains from premature conclusions."}, "familyId": "bmf_1d2d1cba14d5", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_insufficiencybench_debc0b74", "indexedAt": "2026-08-23T06:55:50.392548Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.20220", "pdf": "https://arxiv.org/pdf/2608.20220", "project": null, "report": "https://arxiv.org/abs/2608.20220"}, "metrics": [], "motivation": "Legal AI systems are increasingly used to answer legal questions, yet existing benchmarks assume queries arrive fully specified.", "name": "InsufficiencyBench", "oneLine": "Evaluates whether LLMs recognize legally material missing information in underspecified queries and refrain from premature conclusions.", "paperTitle": "InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.20220", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:50.392548Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-08-20", "source": {"authors": ["Samuel J. Vincent", "Daniel Calloway", "Fangyi Yu", "Andrew M. Bean", "Nabeel Seedat"], "categories": ["cs.AI"], "id": "2608.20220", "title": "InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries", "type": "arxiv", "url": "https://arxiv.org/abs/2608.20220"}, "sourceUpdatedAt": "2026-08-20T16:14:47Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Addresses the practical gap of query-side insufficiency in legal AI, with attorney-annotated items across domains and jurisdictions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
