LLM Latent Reasoning as Chain of Superposition

Understand

Latent reasoning offers a computation-efficient alternative to Chain-of-Thought but often suffers from performance degradation due to distributional misalignment and ambiguous chain definitions.

• Ideally, latent reasoning should function as a superposition of multiple reasoning paths.
• To realize this, we introduce Latent-SFT, a unified framework addressing challenges at three levels: token, chain, and learning.
• First, we define the Latent-Vocab to constrain hidden states within the pre-trained vocab-space.