7 papers
Calibrating Urban Traffic Simulation from Sparse Road Observations via Genetic Optimization
Hunter Sawyer, Jesse Roberts, Simon Matei
Urban traffic simulation is a critical tool for infrastructure planning, including the placement of electric vehicle charging stations. However, realistic traffic simulation across…
Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria
Kelsey Rainey, Jesse Roberts
This paper investigates rubric-aware, multitask fine-tuning of transformer models for automated grading of introductory C++ programming assignments, with the goal of producing grad…
Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
Kyle Moore, Jesse Roberts, Daryl Watson +2
Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis. Primarily to recognize and combat hallucination, the field has largely focus…
KARMA: Karma-Aligned Reward Model Adaptation
Jared Scott, Jesse Roberts
Human communication depends on implicit social signals where effectiveness is shaped by tone, context, and conversational norms rather than semantic content alone. We introduce KAR…
Reinforcement Learning from Meta-Evaluation: Aligning Language Models Without Ground-Truth Labels
Micah Rentschler, Jesse Roberts
Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is…
Exploitation Is All You Need... for Exploration
Micah Rentschler, Jesse Roberts
Ensuring sufficient exploration is a central challenge when training meta-reinforcement learning (meta-RL) agents to solve novel environments. Conventional solutions to the explora…