并行推理综述
A Survey on Parallel Reasoning
AI总结：
本文综述了并行推理，一种通过同时探索多条思路以增强大型语言模型推理鲁棒性的新范式，提出了形式化定义、技术分类、应用场景及未来挑战。
摘要：
随着大型语言模型（LLMs）能力的不断增强，并行推理作为一种新的推理范式应运而生，它通过同时探索多条思路并在最终答案上收敛，从而增强推理的鲁棒性。探索并行推理以克服标准顺序方法的脆弱性并提升实际性能，已成为一个重要趋势。本文旨在调查并总结并行推理的进展与挑战。我们首先给出并行推理的形式化定义，并阐明其与思维链等相关概念的区别。随后，我们基于一种新颖的分类法，组织并讨论了先进技术，包括非交互式推理、交互式推理以及面向效率的解码策略。此外，我们探讨了各种应用场景，例如解决复杂问题和提升LLM输出的可靠性。最后，我们强调了并行推理的核心挑战，并提出了未来研究的潜在方向。我们希望我们的工作能为初学者提供有用的路线图，并鼓励更多关于改进并行推理方法的研究。相关资源可在 https://github.com/PPPP-kaqiu/Awesome-Parallel-Reasoning 获取。
英文摘要：
With the increasing capabilities of Large Language Models (LLMs), parallel reasoning has emerged as a new inference paradigm that enhances reasoning robustness by concurrently exploring multiple lines of thought before converging on a final answer. It has become a significant trend to explore parallel reasoning to overcome the fragility of standard sequential methods and improve practical performance. In this paper, we aim to survey and summarize the progress and challenges of parallel reasoning. We first present a formal definition of parallel reasoning and clarify its distinction from related concepts like Chain-of-Thought. Then, we organize and discuss advanced techniques based on a novel taxonomy, including non-interactive reasoning, interactive reasoning, and efficiency-focused decoding strategies. Additionally, we explore various application scenarios, such as solving complex problems and enhancing the reliability of LLM outputs.Finally, we highlight the core challenges of parallel reasoning and suggest potential directions for future research. We hope that our work can provide a useful roadmap for beginners and encourage more research on improving parallel reasoning methods. Related source can be avaliable in https://github.com/PPPP-kaqiu/Awesome-Parallel-Reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
