让大模型同时答多个问题时更准，减少胡说八道。
MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness
- 分开训练答案生成和置信度判断，提升多问题推理能力。
- 在多问题任务上平均精度比基线高25%。
- 适合需要高可靠性多轮问答的场景，如医疗、法律。
大语言模型产生虚构事实的问题在各类应用中日益突出。以往研究通过分析内部参数化知识边界来估计置信度，但仅限于单问题场景，未探索需同时回答多个问题的复杂情况。本文提出一种新方法——多答案与置信度逐步微调（MAC-Tuning），在指令数据微调过程中分离答案预测与置信度估计的学习。大量实验表明，该方法在多问题设置下平均精度较基线最高提升25%。
原文摘要 · Abstract (English)
The hallucination of non-existent facts by LLMs is an important problem given its widespread adoption across various applications. Previous research addresses this problem by analyzing the internal parameterized knowledge boundaries to estimate confidence. However, these studies focus on the single-problem setting and have not explored the more challenging multi-problem setting, which requires accurately answering multiple questions simultaneously. We introduce a novel method for the multi-problem setting, Multiple Answers and Confidence Stepwise Tuning (MAC-Tuning), that separates the learning of answer prediction and confidence estimation during fine-tuning on instruction data. Extensive experiments demonstrate that our method outperforms baselines by up to 25\% in average precision.
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。