6 papers
Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments
Marthe Ballon, Arne Vanhoyweghen, Seorin Kim +11
Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribute to research synthesis, ev…
Human-in-the-Loop LLM Grading for Handwritten Mathematics Assessments
Arne Vanhoyweghen, Vincent Holst, Melika Mobini +10
Providing timely and individualised feedback on handwritten student work is highly beneficial for learning but difficult to achieve at scale. This challenge has become more pressin…
Ergodicity in reinforcement learning
Dominik Baumann, Erfaun Noorani, Arsenii Mustafin +5
In reinforcement learning, we typically aim to optimize the expected value of the sum of rewards an agent collects over a trajectory. However, if the process generating these rewar…
Model-Agnostic Solutions for Deep Reinforcement Learning in Non-Ergodic Contexts
Bert Verbruggen, Arne Vanhoyweghen, Vincent Ginis
Reinforcement Learning (RL) remains a central optimisation framework in machine learning. Although RL agents can converge to optimal solutions, the definition of ``optimality'' dep…
Metro 3 in Brussels under uncertainty: scenario-based public transport accessibility analysis
Brecht Verbeken, Brecht F. Verbeken, Arne Vanhoyweghen +1
Metro Line 3 in Brussels is one of Europe's most debated infrastructure projects, marked by escalating costs, delays, and uncertainty over completion. Yet no public accessibility a…
Lexical Hints of Accuracy in LLM Reasoning Chains
Arne Vanhoyweghen, Brecht Verbeken, Brecht F. Verbeken +2
Fine-tuning Large Language Models (LLMs) with reinforcement learning to produce an explicit Chain-of-Thought (CoT) before answering produces models that consistently raise overall…