用概率框架提升大模型生成代码的可靠性与可解释性。
Towards a Probabilistic Framework for Analyzing and Improving LLM-Enabled Software
- 通过建模语义等价输出的分布来分析系统性能
- 在自动形式化任务中识别薄弱环节并优化对齐
- 适合关注大模型系统可靠性的开发与研究者
确保大语言模型（LLM）驱动系统的可靠性与可验证性仍是软件工程中的重大挑战。本文提出一种概率框架，通过建模和优化语义等价输出的分布，系统性地分析与改进此类系统。该框架支持对传递模型（Transference Models）的评估与迭代优化，这类关键组件利用LLM将输入转换为下游任务所需输出。为验证其有效性，我们将该框架应用于自然语言文档到正式程序规范的自动形式化问题。结果表明，基于分布的分析能有效识别系统弱点，并指导针对性的对齐改进，从而生成更可靠、更可解释的输出。这一方法为构建鲁棒的LLM驱动系统提供了坚实基础。
原文摘要 · Abstract (English)
Ensuring the reliability and verifiability of large language model (LLM)-enabled systems remains a significant challenge in software engineering. We propose a probabilistic framework for systematically analyzing and improving these systems by modeling and refining distributions over clusters of semantically equivalent outputs. This framework facilitates the evaluation and iterative improvement of Transference Models--key software components that utilize LLMs to transform inputs into outputs for downstream tasks. To illustrate its utility, we apply the framework to the autoformalization problem, where natural language documentation is transformed into formal program specifications. Our case illustrates how distribution-aware analysis enables the identification of weaknesses and guides focused alignment improvements, resulting in more reliable and interpretable outputs. This principled approach offers a foundation for addressing critical challenges in the development of robust LLM-enabled systems.
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。