<ul><li>The research introduces a new model called Graph of Causal Evolution (GoCE) to address limitations in the existing Chain-of-Model (CoM) approach.</li><li>GoCE utilizes a differentiable and sparse causal adjacency matrix to maintain long-range dependencies and overcome global context flow obstructions between subchains.</li><li>Through interventions consistency loss testing and self-evolution gate mechanisms, GoCE achieves a balance between causal structure learning and transformer architecture updating.</li><li>Experimental results demonstrate that GoCE outperforms CoM in capturing long-range causal dependencies and enhancing self-evolution capabilities, providing insights for future causal learning research.</li></ul>

Graph-of-Causal Evolution: Challenging Chain-of-Model for Reasoning

Discover more