用智能修正提示词，让大模型少编瞎话。
CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
- 用小模型自动清理模糊提示，补全任务信息。
- 修正后提示使生成准确率超90%胜过原始提示。
- 无需外部知识，适合所有需要可靠回答的场景。
大语言模型虽能流畅回应各种提问，但常生成看似合理实则错误的‘幻觉’事实，影响可信度。一个常被忽视的原因是用户输入的提示语结构不良或含义模糊，导致模型基于猜测而非真实意图作答。为此，我们提出可即插即用的矫正式提示优化框架CPR：1）清理不良提示；2）利用微调的小模型生成补充任务描述，使用户意图与提示对齐。实验表明，应用CPR后，模型生成质量显著提升，幻觉大幅减少。在无外部知识条件下，采用CPR的提示相比原始提示胜出率超过90%。
原文摘要 · Abstract (English)
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.
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。