Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling Paper • 2605.12411 • Published 14 days ago • 48
Alignment Makes Language Models Normative, Not Descriptive Paper • 2603.17218 • Published Mar 17 • 46
Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software Paper • 2602.04894 • Published Feb 2 • 5