{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.10414", "kind": "paper", "url": "https://arxiv.org/abs/2608.10414"}], "authors": ["Minh Tran", "Trinh Chau", "Thanh-Nhan Le", "Nam Tran", "Luan Thanh Nguyen", "Cuong Dang", "Duc Hoang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.10414", "source_url": "https://arxiv.org/abs/2608.10414"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates LLM robustness to Vietnamese dialectal rewrites across emotion recognition, natural language inference, question answering, and multiple-choice QA, measuring performance degradation across six dialect groups."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.10414", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.10414", "title": "VialectBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Ho Chi Minh City University of Science", "VNU University of Engineering and Technology", "New York University Abu Dhabi", "Vietnam National University Ho Chi Minh City", "University of Information Technology", "Virginia Tech", "Massachusetts Institute of Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.10414", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.10414", "source_url": "https://openalex.org/W7202286378"}, "key": "claire-radar:2608.10414", "modality": null, "name": "VialectBench", "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_vialectbench_c8a2ee22", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "2cf215167a3a61e338657e3b232fb82267d4308e685219f8e3983a2896821248", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.10414"}, "publisher": null, "released": "2026-08-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.10414", "source_url": "https://arxiv.org/abs/2608.10414"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-10414", "source": "claire_radar", "source_benchmark_id": "2608.10414", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.10414", "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": [], "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": "170093ed0814dd2d3c3463a8f2410637b47634d5d52ece9765daf3e6872738a5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLM robustness to Vietnamese dialectal rewrites across emotion recognition, natural language inference, question answering, and multiple-choice QA, measuring performance degradation across six dialect groups.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce VialectBench (Vietnamese Dialects Benchmarking), a controlled benchmark for testing whether model decisions remain stable across six Vietnamese dialect groups."}, "familyId": "bmf_9a6b7205c2c0", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_vialectbench_c8a2ee22", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.10414", "paper": "https://arxiv.org/abs/2608.10414", "pdf": "https://arxiv.org/pdf/2608.10414", "project": null, "report": "https://arxiv.org/abs/2608.10414"}, "metrics": [], "motivation": "Large Language Models (LLMs) are typically evaluated on standard written Vietnamese, yet everyday communication frequently involves regional dialects that preserve meaning but differ in surface form.", "name": "VialectBench", "oneLine": "Evaluates LLM robustness to Vietnamese dialectal rewrites across emotion recognition, natural language inference, question answering, and multiple-choice QA, measuring performance degradation across six dialect groups.", "paperTitle": "How Robust Are LLMs to Vietnamese Dialects?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.10414", "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": "2026-08-11", "source": {"authors": ["Minh Tran", "Trinh Chau", "Thanh-Nhan Le", "Nam Tran", "Luan Thanh Nguyen", "Cuong Dang", "Duc Hoang"], "categories": ["cs.CL", "cs.LG"], "id": "2608.10414", "title": "How Robust Are LLMs to Vietnamese Dialects?", "type": "arxiv", "url": "https://arxiv.org/abs/2608.10414"}, "sourceUpdatedAt": "2026-08-11T03:02:57Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Highlights that model performance on standard Vietnamese does not guarantee reliable behavior under regional variation, informing deployment decisions for Vietnamese-language applications."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
