arXiv cs.CL· Yeon Su Park, Chanyoung Park, Tae Soo Kim, Seungju Kim, Hyunwoo Kim, Daho Jung, Jinsung Yoon, Juho Kim·· 13 小时前AI 评分34
TutorCaseBench：评估 LLM 辅导者应对学生挑战性行为的案例基准
TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors
AI 导读
研究团队推出 TutorCaseBench，一个基于教育学、教育心理学和特殊教育定性案例的 AI 辅导评估基准，包含 923 段对话、覆盖五类挑战行为，含 1,560 道开放式生成题与 2,537 道选择题。在 11 个 SOTA LLM 中，最强模型在开放式场景中仅 55.8% 满足评分标准，且模型选择合适策略的能力强于生成情境化回应，开源权重模型差距尤为明显。数据已公开。
正文 · 原文
Abstract:LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties. We introduce TutorCaseBench, a benchmark that grounds AI-tutor evaluation in qualitative case studies from pedagogy, educational psychology, and special education. Our pipeline converts documented student categories into case-specific scenarios, tutor-student dialogues, and rubrics grounded in source evidence. The benchmark contains 923 dialogues across five challenge types, evaluated through open-ended response generation (1,560 items) and multiple-choice selection (2,537 items). Across 11 state-of-the-art LLMs, even the strongest model satisfies a rubric criterion in only 55.8% of open-ended cases, while models are better at selecting appropriate strategies than generating situated responses. These results reveal a gap between intervention recognition and context-specific adaptation, especially for open-weight models. All data are publicly available at this https URL.
| Comments: | Under Review |
| Subjects: | Computation and Language (cs.CL); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.30828 [cs.CL] |
| (or arXiv:2610.30828v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.30828 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yeon Su Park [view email]
[v1]
Thu, 22 Oct 2026 06:58:46 UTC (11,027 KB)
来源：arXiv cs.CL · arxiv.org