10 citations · 26 across the 16 of their papers we have counts for
17 papers
Beyond State-of-the-Art: Standardising Environmental Impact Metrics for AI Research
Lachlan McGinness, Dan Pagendam, Robert Offner
As the capabilities and ubiquity of Large Language Models (LLMs) grow, so does their environmental footprint. Despite calls for responsible AI, the machine learning community lacks…
Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks
Lachlan McGinness
The deployment of Small Language Models (SLMs) in educational settings offers significant advantages in terms of privacy, cost, and scalability. However, SLMs often struggle with c…
The Benefits and Challenges of a Quantum Computing Concept Inventory
Lachlan McGinness
A Quantum Computing Concept Inventory is needed for the acceleration of uptake of best practice in quantum computing education required to support the quantum computing workforce f…
Making Quantum Accessible: A Seven-Category Framework for K-12 Quantum Education
Rhea Fernandez, Sarah Hagstrom, Liesel Malanos +4
We conducted a literature review and expert interviews to determine the most common methods being used to teach quantum physics and quantum computing concepts to primary and second…
Particle Builder A Board Game for the Teaching of the Standard Model of Particle Physics at a Secondary Level
Lachlan McGinness, Yutong Ma, Mohammad Attar +14
We present Particle Builder, an online board game which teaches students about concepts from the Standard Model of Particle Physics at a high school level. This short activity resu…
Large Language Models Imitate Logical Reasoning, but at what Cost?
Lachlan McGinness, Peter Baumgartner
We present a longitudinal study which evaluates the reasoning capability of frontier Large Language Models over an eighteen month period. We measured the accuracy of three leading…
The AlphaPhysics Term Rewriting System for Marking Algebraic Expressions in Physics Exams
Peter Baumgartner, Lachlan McGinness
We present our method for automatically marking Physics exams. The marking problem consists in assessing typed student answers for correctness with respect to a ground truth soluti…
Particle Builder -- Learn about the Standard Model while playing against an AI
Mohammad Attar, Andrew Carse, Yeming Chen +13
Particle Builder Online is a web-based education game designed for high school physics students. Students can play against an AI opponent or peers to familiarise themselves with th…
Overview of AI Grading of Physics Olympiad Exams
Lachlan McGinness
Automatically grading the diverse range of question types in high school physics problem is a challenge that requires automated grading techniques from different fields. We report…
Large Language Models' Reasoning Stalls: An Investigation into the Capabilities of Frontier Models
Lachlan McGinness, Peter Baumgartner
Empirical methods to examine the capability of Large Language Models (LLMs) to use Automated Theorem Prover (ATP) reasoning strategies are studied. We evaluate the performance of S…
Can Large Language Models Correctly Interpret Equations with Errors?
Lachlan McGinness, Peter Baumgartner
This paper explores the potential of Large Language Models to accurately extract and translate equations from typed student responses into a standard format. This is a useful task…
Highlighting Case Studies in LLM Literature Review of Interdisciplinary System Science
Lachlan McGinness, Peter Baumgartner
Large Language Models (LLMs) were used to assist four Commonwealth Scientific and Industrial Research Organisation (CSIRO) researchers to perform systematic literature reviews (SLR…
CON-FOLD -- Explainable Machine Learning with Confidence
Lachlan McGinness, Peter Baumgartner
FOLD-RM is an explainable machine learning classification algorithm that uses training data to create a set of classification rules. In this paper we introduce CON-FOLD which exten…
Automated Theorem Provers Help Improve Large Language Model Reasoning
Lachlan McGinness, Peter Baumgartner
In this paper we demonstrate how logic programming systems and Automated first-order logic Theorem Provers (ATPs) can improve the accuracy of Large Language Models (LLMs) for logic…
Steamroller Problems: An Evaluation of LLM Reasoning Capability with Automated Theorem Prover Strategies
Lachlan McGinness, Peter Baumgartner
This study presents the first examination of the ability of Large Language Models (LLMs) to follow reasoning strategies that are used to guide Automated Theorem Provers (ATPs). We…
Developing an Action Concept Inventory
Lachlan P. McGinness, C. M. Savage
We report on progress towards the development of an Action Concept Inventory (ACI), a test that measures student understanding of action principles in introductory mechanics and op…
Action Physics
Lachlan P. McGinness, C. M. Savage
More than a decade ago Edwin Taylor issued a "call to action" that presented the case for basing introductory university mechanics teaching around the principle of stationary actio…