模拟有效性：在MLLM生成的科学图表反馈中的模态解耦
Simulating Validity: Modal Decoupling in MLLM Generated Feedback on Science Drawings
AI总结：
研究探讨了多模态大语言模型生成的科学图表反馈中模态解耦问题，发现反馈常存在 grounding 失败，表明需超越常规提示策略的 grounding 机制。
摘要：
在科学教育中，学生常通过手绘视觉模型来构建科学现象。这些图表依赖于一种视觉结构，其中信息通过视觉对象、属性和关系编码。多模态大语言模型（MLLMs）日益被用于生成学生手绘科学模型的反馈。然而，此类反馈的有效性取决于模型主张是否基于学生图表中的具体视觉证据。本研究揭示了现成MLLM反馈中的grounding失败，与模态解耦一致，其中输出在形式上仍具教学合理性，但与图表矛盾或将所绘元素视为缺失。使用N=150名中学生在动能分子理论单元中的150张图表，涵盖五个建模任务和三个能力水平，我们生成了N=300条反馈实例，使用GPT-5.1。所有输出均被编码为四种grounding错误类型：对象不匹配、属性不匹配、关系不匹配和虚假缺失。grounding失败很常见：41.3%的反馈实例至少包含一种错误。采用清单-列表工作流程减少了几个错误类别并降低了总体错误率，但并未解决根本限制：约三分之一的输出仍存在问题，其中虚假缺失是主要失败模式。此外，看似视觉接地的反馈对识别无效实例几乎没有诊断价值。研究结果表明，模态解耦是重大限制，有效的反馈需要超越常规提示策略的grounding机制。
英文摘要：
In science education, students frequently construct hand-drawn visual models of scientific phenomena. These drawings rely on a visual structure where information is encoded through visual objects, their attributes, and relationships. Multimodal large language models (MLLMs) are increasingly used to generate feedback on students' hand-drawn scientific models. However, the validity of such feedback depends on whether model claims are grounded in the specific visual evidence of the student drawing. This study uncovers grounding failures, consistent with modal decoupling, in off-the-shelf MLLM feedback, where outputs remain pedagogically plausible in form while contradicting the drawing or treating depicted elements as missing. Using N = 150 middle school drawings from a kinetic molecular theory unit spanning five modeling tasks and three competence levels, we generated N = 300 feedback instances with GPT-5.1. All outputs were coded for four grounding error types: object mismatch, attribute mismatch, relation mismatch, and false absence. Grounding failures were common: 41.3% of feedback instances contained at least one error. An inventory-list-first workflow reduced several error categories and lowered the overall error rate, but it did not resolve the underlying limitation: approximately one in three outputs remained flawed, with false absence as the dominant failure mode. Moreover, feedback that appears visually grounded offered little diagnostic value for identifying invalid instances. The findings indicate that modal decoupling is a substantial limitation and that valid feedback will require grounding mechanisms beyond common prompting strategies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
