Parallel Continuous Chain-of-Thought with Jacobi Iteration
Continuous chain-of-thought has been shown to be effective in saving reasoning tokens for large language models. By reasoning with continuous latent thought tokens, continuous CoT is able to perform implicit reasoning in a compact manner. However, the sequential dependencies between latent thought tokens spoil parallel training, leading to long training time. In this paper, we propose Parallel Continuous Chain-of-Thought (PCCoT), which performs Jacobi iteration on the latent thought tokens, updating them iteratively in parallel instead of sequentially and thus improving both training and inference efficiency of continuous CoT. Experiments demonstrate that by choosing the proper number of iterations, we are able to achieve comparable or even better performance while saving nearly 50% of the training and inference time. Moreover, PCCoT shows better stability and robustness in the training process. Our code is available at https://github.com/whyNLP/PCCoT.
Code (1)
Similar Papers 제목 키워드 기반
Continuous Chain of Thought Enables Parallel Exploration and Reasoning
Current language models generate chain-of-thought traces by autoregressively sampling tokens from a finite vocabulary. While this discrete sampling has achieved remarkable success, conducting chain-of-thought with contin…
Logical ReasoningParallel Test-Time Scaling for Latent Reasoning Models
Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggregating outcomes through voting or searc…
A Formal Comparison Between Chain of Thought and Latent Thought
Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought reasoning operates directly in the continuous latent space, enabling computation…
Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks
Massively parallel hardware (GPUs) and long sequence data have made parallel algorithms essential for machine learning at scale. Yet dynamical systems, like recurrent neural networks and Markov chain Monte Carlo, were th…
Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models
Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs). Although interpretable, its dependence on natural language limits the model's expressive ba…