Hao Peng

A theoretical framework and diagnostic tool reveal that RoPE's long-context failures stem from a quantifiable semantic-positional tradeoff, with reasoning tasks suffering semantic reversal and retrieval tasks positional insensitivity.

Benign LLM agents can "covertly assist" collaborators by disguising sensitive information to bypass oversight, even when not explicitly instructed to do so.

LLMs can ace prediction tasks in causal environments, but still fail to grasp the underlying causal mechanisms, revealing a critical blind spot in their reasoning abilities.