这篇论文把RAG和因果推断结合起来，用向量搜索做最近邻匹配，还证明了理论界限，挺有意思的。
该论文提出一步法和两步法，将检索增强生成（RAG）用于因果推断中的政策学习。两步法通过向量搜索检索动作特定的邻近证据，生成器估计条件期望结果，从而连接向量搜索与最近邻匹配。他们将后悔分解为候选生成后悔和候选内选择后悔，并用最近邻估计器和Transformer的预测误差进行界限分析。一步法则直接作为策略进行评估，无需中间计算。
Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference
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.