{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.09189", "kind": "paper", "url": "https://arxiv.org/abs/2608.09189"}], "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "EmoSBench evaluates emotional intelligence in spoken language models across four theoretical branches: perceiving, understanding, using, and managing emotion, with ten subtasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.09189", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.09189", "title": "EmoSBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.09189", "modality": null, "name": "EmoSBench", "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_emosbench_d26ab0ed", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "ae0b6cef00a5af058e115426977c7417108c18ab6fcfa28e9c7b75d79f4b146d", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T08:54:07.291235Z", "source_url": "https://arxiv.org/abs/2608.09189"}, "publisher": null, "released": "2026-08-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.09189", "source_url": "https://arxiv.org/abs/2608.09189"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-09189", "source": "claire_radar", "source_benchmark_id": "2608.09189", "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/2608.09189", "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": "Medium", "horizon": "7d", "reason": "Emotional intelligence in speech models is a timely topic and the benchmark's acceptance at a major conference supports early visibility.", "score": 61}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T08:54:07.291235Z", "inputHash": "91963d09edfded82d342ed0ee21de973b279f5b690b6cb402020ee9f3c8c0286", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce EmoSBench, the first comprehensive EI evaluation benchmark for SLMs", "canonicalNameSource": "abstract", "decisionReason": "EmoSBench is formally introduced as an evaluation benchmark with a defined structure and scoring based on accuracy, and the paper is accepted at ACM Multimedia 2026, supporting a public comparison path.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T08:54:07.291235Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EmoSBench evaluates emotional intelligence in spoken language models across four theoretical branches: perceiving, understanding, using, and managing emotion, with ten subtasks.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "We introduce EmoSBench, the first comprehensive EI evaluation benchmark for SLMs constructed upon the four-branch theoretical model, covering Perceiving, Understanding, Using, and Managing Emotion across ten sub-tasks."}, "familyId": "bmf_6842e11fc2c5", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_emosbench_d26ab0ed", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.09189", "pdf": "https://arxiv.org/pdf/2608.09189", "project": null, "report": "https://arxiv.org/abs/2608.09189"}, "metrics": [], "motivation": "Despite significant advances in instruction-following and auditory comprehension, the evaluation of Emotional Intelligence (EI) in Spoken Language Models (SLMs) remains confined to rudimentary paralinguistic perception, lacking a systematic, theory-driven cognitive framework.", "name": "EmoSBench", "oneLine": "EmoSBench evaluates emotional intelligence in spoken language models across four theoretical branches: perceiving, understanding, using, and managing emotion, with ten subtasks.", "paperTitle": "EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at ACM Multimedia 2026 (MM '26)", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.09189", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ACM Multimedia 2026 (MM '26)", "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "publishers": [{"name": "ACM Multimedia 2026", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.09189"}], "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": 0.55, "relation": "evaluates_only", "releasedAt": "2026-08-10", "source": {"authors": ["Junyu Wang", "Siyuan Zhang", "Peiyuan Jiang", "Jian Zong", "Jingyu Zhang", "Tianrui Wang", "Yuqin Lin", "Zhenghui Chen", "Shuqing Xie", "Ziyang Ma", "Meng Ge", "Xiaobao Wang", "Longbiao Wang", "and Jianwu Dang"], "categories": ["cs.CL"], "id": "2608.09189", "title": "EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.09189"}, "sourceUpdatedAt": "2026-08-10T06:58:30Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted at ACM Multimedia 2026 (MM '26)", "evidence": [{"level": "author-claim", "observedAt": "2026-08-19T11:05:13.395391Z", "rawValue": "Accepted at ACM Multimedia 2026 (MM '26)", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.09189"}], "reviewStatus": "accepted", "venueName": "ACM Multimedia 2026 (MM '26)"}], "whyItMatters": "Provides the first theory-driven evaluation standard for emotional intelligence in speech models, exposing significant gaps between current systems and human performance."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
