大模型无需算法即可用提示词求解任意计算问题，突破传统编程范式。
Empirical Computation: Prompting versus Programming
- 用提示词替代编程，让大模型直接生成答案而非逐步计算
- 输出是随机采样而非确定性过程，运行时间与问题复杂度无关
- 呼吁软件工程界建立分析大模型计算正确性的新方法
大型语言模型（LLM）可在不依赖算法的情况下，以与问题计算复杂度无关的运行时间解决任意计算问题。与编写精确程序不同，我们通过提示词引导LLM求解具体问题实例，其输出来自概率分布而非确定性流程。本文作为愿景论文，探讨这种新型计算形式的挑战与机遇，并指出其能力与局限无法用经典理性计算框架理解。因此，我们呼吁软件工程（SE）领域发展基础理论与技术，以分析该‘经验计算’在通用、问题特定或实例特定情形下的正确性。这些研究将为构建经验计算这一新兴方向奠定基础，其具有及时性与丰富性。
原文摘要 · Abstract (English)
Large Language Models (LLM) can solve *any* computational problem *without* an algorithm in a runtime *independent* of the computational complexity of that problem. Instead of specifying precisely how to solve problem instance using *programming*, we ask an LLM to solve the problem instance using *prompting*. Outputs are sampled from a distribution rather than generated procedurally. In this vision paper, we explore the challenges and opportunities of this new form of computation and observe that its capabilities and limits *cannot* be understood within the classic, rationalist framework of computation. Hence, we appeal to the software engineering (SE) community to develop the foundations and techniques required to analyze the properties of this "empirical computation" as it generates solutions to computational problems: How can we analyze and improve the correctness of LLMs solving a computational problem in the general, in the problem-specific, or in the instance-specific? What are the properties and fundamental limits of empirical computation? This paper aims to establish empirical computation as a field in SE that is timely and rich with interesting problems.
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。