Lightweight Latent Reasoning for Narrative Tasks

Understand

Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a query.

• A model's ability to generate such traces can be optimized with reinforcement learning (RL) to improve their utility in predicting an answer.
• This optimization comes at a high computational cost, especially for narrative-related tasks that involve retrieving and processing many tokens.
• To this end, we propose LiteReason, a latent reasoning method that can be interleaved with standard token sampling and easily combined with RL techniques.