CPR：通过治愈性提示精炼缓解大型语言模型幻觉
CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
AI总结：
CPR是一个即插即用框架，通过清理不当提示并生成信息性任务描述来对齐用户意图，从而缓解大型语言模型的幻觉，实验显示其胜率超过90%。
摘要：
大型语言模型（LLMs）的最新进展凸显了它们在响应各种提示时生成流畅内容的能力。然而，这些模型有时会生成看似合理但不正确的“幻觉”事实，削弱了信任。一个常见但常被忽视的此类错误原因是用户使用了结构不良或模糊的提示，导致LLMs基于假设而非实际意图来生成响应。为了缓解由这些不当提示引发的幻觉，我们引入了治愈性提示精炼（CPR），一个即插即用的治愈性提示精炼框架，它能够1）清理不当提示，以及2）使用微调的小语言模型生成额外的信息性任务描述，以对齐用户意图与提示。当应用于语言模型时，我们发现CPR显著提高了生成质量，同时缓解了幻觉。实证研究表明，应用CPR的提示在无需任何外部知识的情况下，相对于原始提示实现了超过90%的胜率。
英文摘要：
Recent advancements in large language models (LLMs) highlight their fluency in generating responses to diverse prompts. However, these models sometimes generate plausible yet incorrect ``hallucinated" facts, undermining trust. A frequent but often overlooked cause of such errors is the use of poorly structured or vague prompts by users, leading LLMs to base responses on assumed rather than actual intentions. To mitigate hallucinations induced by these ill-formed prompts, we introduce Curative Prompt Refinement (CPR), a plug-and-play framework for curative prompt refinement that 1) cleans ill-formed prompts, and 2) generates additional informative task descriptions to align the intention of the user and the prompt using a fine-tuned small language model. When applied to language models, we discover that CPR significantly increases the quality of generation while also mitigating hallucination. Empirical studies show that prompts with CPR applied achieves over a 90\% win rate over the original prompts without any external knowledge.
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。
