3 papers
cs.LG2026
From Human-Level AI Tales to AI Leveling Human Scales
Peter Romero, Fernando Martínez-Plumed, Zachary R. Tidler +11
Comparing AI models to "human level" is often misleading when benchmark scores are incommensurate or human baselines are drawn from a narrow population. To address this, we propose…
cs.LG2025
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
Wanjia Zhao, Qinwei Ma, Jingzhe Shi +7
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks eva…
cs.AI2025
Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models
Stephen Fitz, Peter Romero, Steven Basart +2
Large Language Models increasingly mediate high-stakes interactions, intensifying research on their capabilities and safety. While recent work has shown that LLMs exhibit consisten…