用扩散模型高效生成推理思路，提升大模型推理效率与质量。
Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning
- 用扩散语言模型并行生成多种推理思路，避免逐词生成的耗时
- 在多个基准测试中显著提升复杂推理任务表现，优于传统方法
- 适合追求高效推理的开发者和研究者，尤其关注计算优化场景
近年来，大语言模型（LLMs）在推理能力上取得显著进展，通过测试时扩展策略可有效提升性能。系统评估表明，LLM 能够生成有意识的中间推理步骤，显著提高准确性。然而，其自回归生成范式导致推理性能随测试时计算量增长而次优，需大量计算资源才能获得微小收益。相比之下，扩散语言模型（DLMs）可通过单次前向传播实现并行去噪，高效生成多样化样本。本文提出一种协同推理框架：利用 DLM 生成候选推理步骤，由 LLM 评估其质量。在多个基准测试上的实验表明，该框架在复杂推理任务中表现优异，为未来研究提供了新方向。代码已开源：https://anonymous.4open.science/r/Diffuse-Thinking-EC60。
原文摘要 · Abstract (English)
In recent years, large language models (LLMs) have witnessed remarkable advancements, with the test-time scaling law consistently enhancing the reasoning capabilities. Through systematic evaluation and exploration of a diverse spectrum of intermediate thoughts, LLMs demonstrate the potential to generate deliberate reasoning steps, thereby substantially enhancing reasoning accuracy. However, LLMs' autoregressive generation paradigm results in reasoning performance scaling sub-optimally with test-time computation, often requiring excessive computational overhead to propose thoughts while yielding only marginal performance gains. In contrast, diffusion language models (DLMs) can efficiently produce diverse samples through parallel denoising in a single forward pass, inspiring us to leverage them for proposing intermediate thoughts, thereby alleviating the computational burden associated with autoregressive generation while maintaining quality. In this work, we propose an efficient collaborative reasoning framework, leveraging DLMs to generate candidate thoughts and LLMs to evaluate their quality. Experiments across diverse benchmarks demonstrate that our framework achieves strong performance in complex reasoning tasks, offering a promising direction for future research. Our code is open-source at https://anonymous.4open.science/r/Diffuse-Thinking-EC60.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。