用规则解释大模型如何利用检索信息做决策
Rule-Based Explanations for Retrieval-Augmented LLM Systems
- 通过若-则规则关联检索内容与输出结果
- 仅需少量测试即可生成有效解释规则
- 适合需要透明决策的AI应用开发者
if-then规则广泛用于解释机器学习模型；例如，'若未就业，则贷款申请被拒'。本文首次提出将规则应用于检索增强型大语言模型（RAG）的解释。由于RAG可在推理时引入检索信息源，因此可通过规则关联源的存在与否与输出结果；例如，'若检索到《泰晤士高等教育》排名文章，则模型将牛津大学排第一'。为生成此类规则，传统暴力方法需测试所有源组合并验证其对输出的影响。我们提出优化方案，受频繁项集挖掘中Apriori剪枝启发，但针对本问题重新定义。定性与定量实验表明，该方法在生成效率与解释价值上均具优势。
原文摘要 · Abstract (English)
If-then rules are widely used to explain machine learning models; e.g., "if employed = no, then loan application = rejected." We present the first proposal to apply rules to explain the emerging class of large language models (LLMs) with retrieval-augmented generation (RAG). Since RAG enables LLM systems to incorporate retrieved information sources at inference time, rules linking the presence or absence of sources can explain output provenance; e.g., "if a Times Higher Education ranking article is retrieved, then the LLM ranks Oxford first." To generate such rules, a brute force approach would probe the LLM with all source combinations and check if the presence or absence of any sources leads to the same output. We propose optimizations to speed up rule generation, inspired by Apriori-like pruning from frequent itemset mining but redefined within the scope of our novel problem. We conclude with qualitative and quantitative experiments demonstrating our solutions' value and efficiency.
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。