{"record": {"aliases": ["RESCUE-BENCH"], "artifacts": [{"id": "arxiv:2609.09657", "kind": "paper", "url": "https://arxiv.org/abs/2609.09657"}], "authors": ["Haichuan Hu", "Yang Xiao", "Mingni Tang", "Jiawen Duan", "Quanjun Zhang", "Congqing He", "Hao Zhang", "Jiashuo Wang", "Johan F. Hoorn", "Wenjie Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.09657", "source_url": "https://arxiv.org/abs/2609.09657"}, "categories": ["General AI", "Vision & 3D", "cs.AI"], "description": {"en": "Evaluates LLMs on relation-aware emotional support through six tasks derived from couple and family interview conversations, assessing relational understanding and relation-sensitive support."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.09657", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.09657", "title": "RESCUE"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hong Kong Polytechnic University", "Nanjing University of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.09657", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.09657", "source_url": "https://openalex.org/W7212185928"}, "key": "claire-radar:2609.09657", "modality": null, "name": "RESCUE", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "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_rescue-bench_e82c01f3", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "12c447be6247649c5754246548568d745733b82bd6833d8e87f4b23ac4b42c1f", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-11T00:52:53.785364Z", "source_url": "https://arxiv.org/abs/2609.09657"}, "publisher": null, "released": "2026-09-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.09657", "source_url": "https://arxiv.org/abs/2609.09657"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-09657", "source": "claire_radar", "source_benchmark_id": "2609.09657", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["RESCUE-BENCH"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-09-10", "attemptedAt": "2026-09-10T12:24:43.080049Z", "githubRepo": "https://github.com/Tomsawyerhu/RESCUE-bench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": "2026-09-10T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 2, "hfPaperUrl": "https://huggingface.co/papers/2609.09657", "observedAt": "2026-09-10T12:24:43.080049Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-10T12:24:43.080049Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-09-10T12:24:43.080049Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Niche focus on emotional support and limited public artifact visibility may cap initial traction despite novel multi-party aspect.", "score": 35}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-11T00:52:53.785364Z", "inputHash": "00b8c2ff8c5b36b1b14791d61f1f3904c696506677bc43fb67cf7230d01476fd", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We construct RESCUE (Relation-aware Emotional Support Conversation Understanding and Evaluation Benchmark)", "canonicalNameSource": "abstract", "decisionReason": "Data sizes and task definitions are explicit, though no direct data link; benchmark identity is clear and reusable.", "evaluationEvidence": {"reuse": "contains 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video", "scoring": "Experiments with ten LLMs show that current models perform relatively well on tasks relying on local emotional or intervention cues, but struggle with relation-intensive tasks such as relation pattern prediction, viewpoint prediction, and support strategy prediction.", "task": "six tasks that evaluate two core capabilities required for relation-aware emotional support: Relational Understanding and Relation-Sensitive Support"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-11T00:52:53.785364Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLMs on relation-aware emotional support through six tasks derived from couple and family interview conversations, assessing relational understanding and relation-sensitive support.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "evaluation protocol evidence"], "snippet": "We construct RESCUE (Relation-aware Emotional Support Conversation Understanding and Evaluation Benchmark) from real couple and family interview conversations, containing 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video."}, "familyId": "bmf_6b6323c23009", "firstSeenAt": "2026-09-10", "heat": null, "id": "bm_rescue-bench_e82c01f3", "indexedAt": "2026-09-10T00:47:26.889471Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.09657", "pdf": "https://arxiv.org/pdf/2609.09657", "project": null, "report": "https://arxiv.org/abs/2609.09657"}, "metrics": [], "motivation": "Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interpersonal relations in multi-party scenarios underexplored.", "name": "RESCUE", "oneLine": "Evaluates LLMs on relation-aware emotional support through six tasks derived from couple and family interview conversations, assessing relational understanding and relation-sensitive support.", "paperTitle": "RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems", "primaryDomain": "General AI", "publication": {"evidence": "accepted as AACL findings", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.09657", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "as AACL findings", "verifiedAt": "2026-09-10T00:47:26.889471Z"}, "publications": [], "ranking": {"30d": {"confidence": "High", "coverage": 0.85, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.10323645750017778, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.19460147417678111, "value": 2}}, "confidence": "High", "coverage": 0.85, "rank": 226, "score": 19}, "method": "attention-ranking-v13", "rank": 226, "score": 19}, "90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.09355303223343062, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.19460147417678111, "value": 2}}, "confidence": "Medium", "coverage": 0.7, "rank": 334, "score": 23}, "method": "attention-ranking-v13", "rank": 334, "score": 23}, "today": {"confidence": "Medium", "coverage": 0.7, "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": 1, "historyDate": "2026-09-09", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": 0.6666666666666666, "percentile": 0.6666666666666666, "value": 1}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": 0.5, "percentile": 0.5, "value": 2}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.58, "role": "bonus", "value": 58}}, "confidence": "Medium", "coverage": 0.7, "rank": 2, "score": 56}, "method": "attention-ranking-v13", "rank": 2, "score": 56}}, "readiness": "Paper only", "recognitionConfidence": 0.65, "relation": "introduces", "releasedAt": "2026-09-09", "source": {"authors": ["Haichuan Hu", "Yang Xiao", "Mingni Tang", "Jiawen Duan", "Quanjun Zhang", "Congqing He", "Hao Zhang", "Jiashuo Wang", "Johan F. Hoorn", "Wenjie Li"], "categories": ["cs.AI"], "id": "2609.09657", "title": "RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems", "type": "arxiv", "url": "https://arxiv.org/abs/2609.09657"}, "sourceUpdatedAt": "2026-09-09T03:14:13Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "accepted as AACL findings", "evidence": [{"level": "author-claim", "observedAt": "2026-09-10T00:47:26.889471Z", "rawValue": "accepted as AACL findings", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.09657"}], "reviewStatus": "accepted", "venueName": "as AACL findings"}], "whyItMatters": "Highlights limitations in modeling interpersonal dynamics for emotional support, guiding development of relation-sensitive systems for multi-party scenarios."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
