TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance
This addresses efficiency for LLM deployment, but appears incremental as it builds on existing distillation techniques.
The paper tackles the problem of high computational costs from increased output tokens when LLMs use reasoning processes, by proposing TwT which reduces inference-time costs while maintaining performance. It achieves up to 13.6% accuracy improvement with fewer output tokens compared to other distillation methods.
Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes. However, this enhanced reasoning capability results in an increased number of output tokens during inference, leading to higher computational costs. To address this challenge, we propose TwT (Thinking without Tokens), a method that reduces inference-time costs through habitual reasoning distillation with multi-teachers' guidance, while maintaining high performance. Our approach introduces a Habitual Reasoning Distillation method, which internalizes explicit reasoning into the model's habitual behavior through a Teacher-Guided compression strategy inspired by human cognition. Additionally, we propose Dual-Criteria Rejection Sampling (DCRS), a technique that generates a high-quality and diverse distillation dataset using multiple teacher models, making our method suitable for unsupervised scenarios. Experimental results demonstrate that TwT effectively reduces inference costs while preserving superior performance, achieving up to a 13.6% improvement in accuracy with fewer output tokens compared to other distillation methods, offering a highly practical solution for efficient LLM deployment.