SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fawzi, Fares, Swamy, Vinitra, Glandorf, Dominik, Nazaretsky, Tanya, Käser, Tanja
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917050328285184
author Fawzi, Fares
Swamy, Vinitra
Glandorf, Dominik
Nazaretsky, Tanya
Käser, Tanja
author_facet Fawzi, Fares
Swamy, Vinitra
Glandorf, Dominik
Nazaretsky, Tanya
Käser, Tanja
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26322
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling
Fawzi, Fares
Swamy, Vinitra
Glandorf, Dominik
Nazaretsky, Tanya
Käser, Tanja
Computation and Language
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.
title SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling
topic Computation and Language
url https://arxiv.org/abs/2510.26322