让大模型决策更可信，通过精准检索提升判断可靠性
Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation
- 引入校准导向的检索机制，确保生成内容与真实信心匹配
- 在多个数据集上验证，显著提升决策准确率与校准度
- 适合需要高可靠性决策的应用场景，如医疗、金融
大语言模型（LLMs）正广泛用于辅助决策，但其自信地输出错误信息可能导致人类做出次优判断。现有检索增强生成（RAG）方法仅关注查询相关文档的检索，未专门保证用户决策的校准性。为此，我们提出校准导向的检索增强生成（CalibRAG），确保基于RAG的决策具备良好校准性。实证结果表明，相比其他基线方法，CalibRAG在多个数据集上均显著提升了校准性能与准确性。
原文摘要 · Abstract (English)
Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confidently provide incorrect information, it can lead humans to make suboptimal decisions. To prevent LLMs from generating incorrect information on topics they are unsure of and to improve the accuracy of generated content, prior works have proposed Retrieval Augmented Generation (RAG), where external documents are referenced to generate responses. However, previous RAG methods focus only on retrieving documents most relevant to the input query, without specifically aiming to ensure that the human user's decisions are well-calibrated. To address this limitation, we propose a novel retrieval method called Calibrated Retrieval-Augmented Generation (CalibRAG), which ensures that decisions informed by RAG are well-calibrated. Then we empirically validate that CalibRAG improves calibration performance as well as accuracy, compared to other baselines across various datasets.
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。