小模型也能精准解释学生反馈，还支持纠错和工具调用。
SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling
- 用工具辅助的多跳推理+自我反思机制，提升回答准确性。
- 3B和8B小模型经两阶段微调后，表现接近大模型GPT-4o。
- 适合教育场景中需本地运行、保护隐私的个性化反馈系统。
语言模型可用于教育场景中提供交互式、个性化的学生反馈。然而实际部署面临三大挑战：隐私顾虑、计算资源有限，以及需要符合教学逻辑的回应。这要求小型开源模型能在本地可靠运行，并准确依据正确信息生成输出。我们提出SCRIBE框架，用于多跳、工具增强的推理，以生成关于反馈报告的学生问题的有效回答。SCRIBE结合领域专用工具与自省式推理流程，支持迭代推理、工具调用与错误恢复。通过在合成GPT-4o生成数据上进行两阶段LoRA微调，将这些能力蒸馏至3B和8B模型。使用人类对齐的GPT-Judge评估及108名学生的用户研究显示，8B-SCRIBE模型在相关性与可操作性等关键维度上达到甚至超过更大模型的表现，且被学生评价为与GPT-4o和Llama-3.3 70B相当。结果证明SCRIBE在低资源、隐私敏感的教育应用中具备可行性。
原文摘要 · Abstract (English)
Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for pedagogically valid responses. These constraints require small, open-source models that can run locally and reliably ground their outputs in correct information. We introduce SCRIBE, a framework for multi-hop, tool-augmented reasoning designed to generate valid responses to student questions about feedback reports. SCRIBE combines domain-specific tools with a self-reflective inference pipeline that supports iterative reasoning, tool use, and error recovery. We distil these capabilities into 3B and 8B models via two-stage LoRA fine-tuning on synthetic GPT-4o-generated data. Evaluation with a human-aligned GPT-Judge and a user study with 108 students shows that 8B-SCRIBE models achieve comparable or superior quality to much larger models in key dimensions such as relevance and actionability, while being perceived on par with GPT-4o and Llama-3.3 70B by students. These findings demonstrate the viability of SCRIBE for low-resource, privacy-sensitive educational applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。