向量搜索作为最近邻匹配：因果推断中基于检索增强生成（RAG）的策略学习
Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference
浏览论文内容
中文总结 AI 辅助
研究提出基于检索增强生成（RAG）的策略学习一步法和两步法，两步法通过向量搜索等进行行动选择，还将两步法遗憾分解并界定，直接评估一步法为策略，把特定行动向量搜索与因果推断最近邻匹配相联系。
中文摘要 AI 辅助
我们提出了用于基于检索增强生成（RAG）的策略学习的一步法和两步法。在潜在结果框架下制定基于RAG的行动选择。两步法中，向量搜索在嵌入空间中检索特定行动的相邻证据，生成器估计条件期望结果或其对比，插件规则选择行动。此公式将特定行动的向量搜索与因果推断中的最近邻匹配联系起来。我们将两步法的遗憾分解为候选生成遗憾和候选内选择遗憾，并利用最近邻估计器和变压器的预测误差保证来界定后者。由于一步法的中间计算不可观测，我们直接将其评估为一种策略。
英文摘要
We propose one-step and two-step methods for policy learning with retrieval-augmented generation (RAG). We formulate RAG-based action selection under the potential outcome framework. In the two-step method, vector search retrieves action-specific neighboring evidence in an embedding space, the generator estimates conditional expected outcomes or their contrasts, and a plug-in rule selects an action. This formulation connects action-specific vector search with nearest-neighbor matching in causal inference. We decompose the regret of the two-step method into candidate-generation regret and within-candidate choice regret, and we bound the latter using prediction-error guarantees for nearest-neighbor estimators and transformers. We evaluate the one-step method directly as a policy because its intermediate computation is unobserved.
发表机构
- np-hard.co.jp（np-hard公司）
机构由 AI 辅助整理，请以论文原文为准。
