{"record": {"aliases": ["EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages"], "artifacts": [{"id": "arxiv:2609.05043", "kind": "paper", "url": "https://arxiv.org/abs/2609.05043"}], "authors": ["Aleix Sant", "Jordi Luque", "Carlos Escolano"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.05043", "source_url": "https://arxiv.org/abs/2609.05043"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "A multilingual benchmark for verifiable instruction following, derived from IFEval and localized to 50 European languages and regional varieties via task-preserving translation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.05043", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.05043", "title": "European-IFEval"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Universitat Politècnica de Catalunya"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.05043", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.05043", "source_url": "https://openalex.org/W7211883434"}, "key": "claire-radar:2609.05043", "modality": null, "name": "European-IFEval", "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": "false", "origin_record_id": "bm_euroalpaca-task-preserving-localisation-of_6eb5fc44", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "75a9bfeb741c108eaea84aa12ed2e8842a2187c14adb12d0ddbfc0e5c7682d8e", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-08T06:12:48.315092Z", "source_url": "https://arxiv.org/abs/2609.05043"}, "publisher": null, "released": "2026-09-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.05043", "source_url": "https://arxiv.org/abs/2609.05043"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-05043", "source": "claire_radar", "source_benchmark_id": "2609.05043", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages"], "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": null, "hfPaperUrl": "https://huggingface.co/papers/2609.05043", "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": "The relevance to multilingual NLP may draw attention, but the lack of public artifacts limits immediate engagement.", "score": 35}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:59:06.803818Z", "inputHash": "e34fc1d0fc1a0a446fec26b8084c4ff41afeeb602305063347cb71620d2202ad", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "together with European-IFEval, a multilingual benchmark for verifiable instruction following", "canonicalNameSource": "abstract", "decisionReason": "No evidence of a public code, data, or protocol release path for other teams to run or inspect the benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-08T06:12:48.315092Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A multilingual benchmark for verifiable instruction following, derived from IFEval and localized to 50 European languages and regional varieties via task-preserving translation.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce EuroAlpaca, a task-preserving localisation pipeline and near-parallel resource covering 50 European languages and regional varieties, together with European-IFEval, a multilingual benchmark for verifiable instruction following."}, "familyId": "bmf_2529b2b354db", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_euroalpaca-task-preserving-localisation-of_6eb5fc44", "indexedAt": "2026-09-07T06:22:02.605340Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.05043", "pdf": "https://arxiv.org/pdf/2609.05043", "project": null, "report": "https://arxiv.org/abs/2609.05043"}, "metrics": [], "motivation": "Machine translation (MT) offers a scalable way to extend English instruction-tuning data to multiple languages, but it can distort task-critical constraints and required outputs, creating corrupted training examples and degrading models trained on such data.", "name": "European-IFEval", "oneLine": "A multilingual benchmark for verifiable instruction following, derived from IFEval and localized to 50 European languages and regional varieties via task-preserving translation.", "paperTitle": "EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.05043", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T06:22:02.605340Z"}, "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": 0.6, "relation": "introduces", "releasedAt": "2026-09-04", "source": {"authors": ["Aleix Sant", "Jordi Luque and Carlos Escolano"], "categories": ["cs.CL"], "id": "2609.05043", "title": "EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages", "type": "arxiv", "url": "https://arxiv.org/abs/2609.05043"}, "sourceUpdatedAt": "2026-09-04T12:05:53Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Assesses instruction-following accuracy across European languages, crucial for evaluating multilingual instruction-tuned models and detecting degradation from direct machine translation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
