Doug Holton

arXiv.org

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems

Large language models are rapidly being deployed as AI tutors, yet current evaluation paradigms assess problem-solving accuracy and generic safety in isolation, failing to capture whether a model is simultaneously pedagogically effective and safe across student-tutor interaction. We argue that tutoring safety is fundamentally different from conventional LLM safety: the primary risk is not toxic content but the quiet erosion of learning through answer over-disclosure, misconception reinforcement,

UCL Press

ABC Learning Design

An accessible guide to ABC Learning Design, showcasing its rapid, collaborative method and global adaptations that support innovative, flexible curriculum design.

arXiv.org

The LLM Fallacy: Misattribution in AI-Assisted Cognitive Workflows

The rapid integration of large language models (LLMs) into everyday workflows has transformed how individuals perform cognitive tasks such as writing, programming, analysis, and multilingual communication. While prior research has focused on model reliability, hallucination, and user trust calibration, less attention has been given to how LLM usage reshapes users' perceptions of their own capabilities. This paper introduces the LLM fallacy, a cognitive attribution error in which individuals misi

arXiv.org

Evolution of AI in Education: Agentic Workflows

The primary goal of this study is to analyze agentic workflows in education according to the proposed four major technological paradigms: reflection, planning, tool use, and multi-agent collaboration. We critically examine the role of AI agents in education through these key design paradigms, exploring their advantages, applications, and challenges. Second, to illustrate the practical potential of agentic systems, we present a proof-of-concept application: a multi-agent framework for automated e

GitHub - LadybugDB/ladybug: LadybugDB a graph database

LadybugDB a graph database. Contribute to LadybugDB/ladybug development by creating an account on GitHub.

Alfie Kohn: "1/3 Superb new book by Nick Chater & George Loewe…" - sciences.social

Federal Register

Extension of Compliance Dates for Nondiscrimination on the Basis of Disability; Accessibility of Web Information and Services of State and Local Government Entities

By this Interim Final Rule ("IFR"), the Department of Justice ("Department") is revising the regulations implementing title II of the Americans with Disabilities Act ("ADA") to extend the compliance dates for the requirements for web content and mobile application ("app") accessibility that were...

Cambridge Core

Academic Integrity in the Age of AI

Cambridge Core - Teacher training and professional development - Academic Integrity in the Age of AI

arXiv.org

ISD-Agent-Bench: A Comprehensive Benchmark for Evaluating LLM-based Instructional Design Agents

Large Language Model (LLM) agents have shown promising potential in automating Instructional Systems Design (ISD), a systematic approach to developing educational programs. However, evaluating these agents remains challenging due to the lack of standardized benchmarks and the risk of LLM-as-judge bias. We present ISD-Agent-Bench, a comprehensive benchmark comprising 25,795 scenarios generated via a Context Matrix framework that combines 51 contextual variables across 5 categories with 33 ISD sub

Python on Windows for beginners

A guide to help you get started if your brand new to using Python on Windows.

arXiv.org

Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning

We present an innovative multi-stage optimization strategy combining reinforcement learning (RL) and supervised fine-tuning (SFT) to enhance the pedagogical knowledge of large language models (LLMs), as illustrated by EduQwen 32B-RL1, EduQwen 32B-SFT, and an optional third-stage model EduQwen 32B-SFT-RL2: (1) RL optimization that implements progressive difficulty training, focuses on challenging examples, and employs extended reasoning rollouts; (2) a subsequent SFT phase that leverages the RL-t

liascript.github.io

Lia

LiaScript is a service for running free and interactive online courses, build with its own Markup-language. So check out the following course ;-)