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 withi
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 84%xorbitsai/inference →
“Fuzzy title match (0.92): “Vector Search As Nearest Neighbor Matching: RAG-based Policy” ≈ “xorbitsai/inference””
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Vector Search As Nearest Neighbor Matching: RAG-based Policy” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Masahiro Kato →
“Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference”
- LinkedLinked via arxiv author · 85%Taka Kato →
“Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference”