7 papers
Human agency in initial human-AI proof formalization workflows
Katherine M. Collins, Simon Frieder, Jonas Bayer +14
For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been…
From Human-Level AI Tales to AI Leveling Human Scales
Peter Romero, Fernando MartÃnez-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…
Social-R1: Towards Human-like Social Reasoning in LLMs
Jincenzi Wu, Yuxuan Lei, Jianxun Lian +5
While large language models demonstrate remarkable capabilities across numerous domains, social intelligence - the capacity to perceive social cues, infer mental states, and genera…
Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models
Zongqian Li, Shaohan Huang, Zewen Chi +5
Modern code generation models exhibit longer outputs, accelerated capability growth, and changed training dynamics, rendering traditional training methodologies, algorithms, and da…
PredictaBoard: Benchmarking LLM Score Predictability
Lorenzo Pacchiardi, Konstantinos Voudouris, Ben Slater +4
Despite possessing impressive skills, Large Language Models (LLMs) often fail unpredictably, demonstrating inconsistent success in even basic common sense reasoning tasks. This unp…
General Scales Unlock AI Evaluation with Explanatory and Predictive Power
Lexin Zhou, Lorenzo Pacchiardi, Fernando MartÃnez-Plumed +23
Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activitie…