构建了5倍于前人的LLM生产管道验证数据集，助力提升模型输出可靠性。
PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines
- 收集2087个真实生产场景提示与12623条校验规则，来自开源工具用户实践。
- 微调的Mistral和Llama 3在生成校验规则上比GPT-4o平均高20.93%准确率。
- 适合研究LLM对齐、可靠推理与提示工程的开发者与研究人员使用。
大型语言模型（LLMs）正被广泛部署于金融、营销、电商等领域的专用生产数据处理流程中。然而，在面对大量输入时，这些模型常无法遵循指令或满足开发者预期。为提升应用可靠性，需在流水线中加入输出断言或防护机制。但如何确定能准确捕捉任务需求的断言集合仍具挑战。本文提出PROMPTEVALS，一个包含2087个LLM流水线提示及12623条对应断言标准的数据集，来源自使用我们开源工具的开发者。该数据集规模是先前集合的5倍。基于其留出测试集，我们评估了闭源与开源模型生成相关断言的能力。显著地，我们微调的Mistral和Llama 3模型在平均性能上优于GPT-4o达20.93%，同时具备更低延迟。我们认为该数据集将推动LLM可靠性、对齐性与提示工程的进一步研究。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly deployed in specialized production data processing pipelines across diverse domains -- such as finance, marketing, and e-commerce. However, when running them in production across many inputs, they often fail to follow instructions or meet developer expectations. To improve reliability in these applications, creating assertions or guardrails for LLM outputs to run alongside the pipelines is essential. Yet, determining the right set of assertions that capture developer requirements for a task is challenging. In this paper, we introduce PROMPTEVALS, a dataset of 2087 LLM pipeline prompts with 12623 corresponding assertion criteria, sourced from developers using our open-source LLM pipeline tools. This dataset is 5x larger than previous collections. Using a hold-out test split of PROMPTEVALS as a benchmark, we evaluated closed- and open-source models in generating relevant assertions. Notably, our fine-tuned Mistral and Llama 3 models outperform GPT-4o by 20.93% on average, offering both reduced latency and improved performance. We believe our dataset can spur further research in LLM reliability, alignment, and prompt engineering.
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。