Chuan Xiao

The paper introduces Prosecution Decision Prediction (PDP), a new legal AI task that assesses prosecutorial review decisions, showing that current state-of-the-art LLMs perform significantly worse on this task than on standard judgment prediction.

The paper decomposes LLM debate convergence into three mechanisms (instability, conformity, persuasion) and finds that much observed convergence is harmful social compliance rather than genuine reasoning.

The paper proposes using emergent language (EL) in multi-agent reinforcement learning, where agents develop communication from minimal starting conditions, to study consciousness-relevant structures independent of human language biases.