{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.10428", "kind": "paper", "url": "https://arxiv.org/abs/2607.10428"}], "authors": ["Jinglan Gong", "Jiefan Lu", "Hewei Guo", "Kehan Li", "Zhiyuan Han", "Jihang Jiang", "Wenwen Tong", "Lewei Lu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.10428", "source_url": "https://arxiv.org/abs/2607.10428"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "EYT-Bench evaluates multi-turn dialogue capabilities of LLMs using a decoupled three-party setup with user simulation, target modeling, and judging."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.10428", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.10428", "title": "EYT-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Science and Technology of China", "Sensetime (China)", "Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.10428", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.10428", "source_url": "https://openalex.org/W7168236853"}, "key": "claire-radar:2607.10428", "modality": null, "name": "EYT-Bench", "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_eyt-bench_32cb0b9c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f49e5271dd7268064abb0877e108e689dbe9b9324feebaada3620f391c3a3870", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.10428"}, "publisher": null, "released": "2026-07-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.10428", "source_url": "https://arxiv.org/abs/2607.10428"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-10428", "source": "claire_radar", "source_benchmark_id": "2607.10428", "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": 1, "hfPaperUrl": "https://huggingface.co/papers/2607.10428", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "10404f1d93198eb060bae2c1f9faa113cc8879b19b7cc5375fd9b11ece7f035a", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EYT-Bench evaluates multi-turn dialogue capabilities of LLMs using a decoupled three-party setup with user simulation, target modeling, and judging.", "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 EYT-Bench, a human-centered benchmark whose evaluation protocol is built around a decoupled three-party design: a persona-grounded user simulator, a target model evaluated on both intent perception and response generation, and an independent, configurable ensemble of LLM judges."}, "familyId": "bmf_67a637fc68e9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_eyt-bench_32cb0b9c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.10428", "paper": "https://arxiv.org/abs/2607.10428", "pdf": "https://arxiv.org/pdf/2607.10428", "project": null, "report": "https://arxiv.org/abs/2607.10428"}, "metrics": [], "motivation": "Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: persona consistency, evolving intent tracking, emotional dynamics, and goal completion across many turns.", "name": "EYT-Bench", "oneLine": "EYT-Bench evaluates multi-turn dialogue capabilities of LLMs using a decoupled three-party setup with user simulation, target modeling, and judging.", "paperTitle": "Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.10428", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "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": 0.12247537038455211, "value": 1}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 44}, "method": "attention-ranking-v13", "rank": null, "score": 44}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-11", "source": {"authors": ["Jinglan Gong", "Jiefan Lu", "Hewei Guo", "Kehan Li", "Zhiyuan Han", "Jihang Jiang", "Wenwen Tong", "Lewei Lu"], "categories": ["cs.CL"], "id": "2607.10428", "title": "Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging", "type": "arxiv", "url": "https://arxiv.org/abs/2607.10428"}, "sourceUpdatedAt": "2026-07-24T14:32:58Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Assessing conversational AI beyond single turns may guide development of more consistent and context-aware dialogue systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
