LLM Essay Scoring: Bias and Prompt Effects in Rubrics
Explore how LLMs score essays under holistic and analytic rubrics, revealing bias and prompt impacts for fairer AI-assisted assessments.
Hierarchical Apprenticeship Learning with Evolving Rewards
Discover HALIDE, a hierarchical apprenticeship learning method that leverages imperfect demonstrations and evolving rewards to improve e-learning outcomes.
REM-CTX: Reinforcement Learning for Automated Peer Review
Discover REM-CTX, an advanced system using reinforcement learning and auxiliary context to improve automated peer review accuracy and quality.
Softmax Policy for Risk-Averse Multi-Armed Bandits
Explore a softmax gradient policy designed to minimize variance and enhance risk-averse decision-making in multi-armed bandit problems.
AI-Driven Explainable Regulation for Fair Justice
Discover how AI-driven explainable regulation enhances transparency, adaptability, and fairness in justice systems to combat bias and improve compliance.