{"record": {"aliases": ["Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts"], "artifacts": [{"id": "arxiv:2608.24707", "kind": "paper", "url": "https://arxiv.org/abs/2608.24707"}], "authors": ["Meruyert Aristombayeva", "Jason S. Lucas", "Chaewan Chun", "Dongwon Lee"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.24707", "source_url": "https://arxiv.org/abs/2608.24707"}, "categories": ["General AI", "Vision & 3D", "cs.CL"], "description": {"en": "A multilingual spoken hallucination detection benchmark with 12,013 news samples across English, Russian, and Kazakh, including synthetic and real-world fake news items in text and audio."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.24707", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.24707", "title": "Lost in Speech"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.24707", "modality": null, "name": "Lost in Speech", "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_lost-in-speech-trilingual-spoken-hallucina_f3c90115", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "1adfab13431cad8f95d07bf361523ad24568add4e0066cc92136e5da0ef872c7", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:08:47.245811Z", "source_url": "https://arxiv.org/abs/2608.24707"}, "publisher": null, "released": "2026-08-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.24707", "source_url": "https://arxiv.org/abs/2608.24707"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-24707", "source": "claire_radar", "source_benchmark_id": "2608.24707", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts"], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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/2608.24707", "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": "Niche topic but relevance to multilingual NLP may attract moderate interest; no public artifacts to drive visibility.", "score": 40}, "capabilities": [], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:22:25.189955Z", "inputHash": "7296574b009f67d46eac73320bb119a08e8b5f77b862516c10c2cdebf5ce692a", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts", "canonicalNameSource": "paper_title", "decisionReason": "Explicit benchmark corpus with controlled construction, real-world extensions, defined evaluation tasks (transcript vs audio), and results across multiple models.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:08:47.245811Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A multilingual spoken hallucination detection benchmark with 12,013 news samples across English, Russian, and Kazakh, including synthetic and real-world fake news items in text and audio.", "displayEligible": true, "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 present the first multilingual spoken hallucination benchmark comprising 12,013 news samples across English, Russian, and Kazakh with controlled hallucinations of three types and three severity levels."}, "familyId": "bmf_adb8b355243f", "firstSeenAt": "2026-08-26", "heat": null, "id": "bm_lost-in-speech-trilingual-spoken-hallucina_f3c90115", "indexedAt": "2026-08-26T06:08:22.244942Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.24707", "pdf": "https://arxiv.org/pdf/2608.24707", "project": null, "report": "https://arxiv.org/abs/2608.24707"}, "metrics": [], "motivation": "While text-based hallucination detection has been extensively studied, spoken hallucination detection remains largely unexplored, particularly for low-resource languages.", "name": "Lost in Speech", "oneLine": "A multilingual spoken hallucination detection benchmark with 12,013 news samples across English, Russian, and Kazakh, including synthetic and real-world fake news items in text and audio.", "paperTitle": "Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.24707", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-26T06:08:22.244942Z"}, "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": "2026-08-25", "source": {"authors": ["Meruyert Aristombayeva", "Jason S. Lucas", "Chaewan Chun", "Dongwon Lee"], "categories": ["cs.CL"], "id": "2608.24707", "title": "Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts", "type": "arxiv", "url": "https://arxiv.org/abs/2608.24707"}, "sourceUpdatedAt": "2026-08-25T15:24:48Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the gap in spoken hallucination detection, especially for low-resource languages, and evaluates transfer from synthetic to real-world fake news."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
