Publication Date

Spring 2026

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

First Advisor

Robert Chun

Second Advisor

Sayma Akther

Third Advisor

Genya Ishigaki

Keywords

Retrieval-Augmented Generation, Conformal Calibration, Multi-Rung Retrieval, Uncertainty Estimation, Risk-Controlled Question Answering

Abstract

Retrieval-Augmented Generation (RAG) improves factual grounding in large language models by incorporating external evidence during inference. However, most RAG systems rely on fixed retrieval strategies that ignore query difficulty, computational cost, and prediction uncertainty. This project introduces SAFE-R2R (Safety-Aware and Budget-Optimized Reason-to-Retrieve), a retrieval controller that treats retrieval as a query-dependent decision problem. SAFE-R2R organizes retrieval into a multi-rung ladder ranging from no retrieval to deeper retrieval with reranking. At each rung, the system generates an answer, computes reliability signals, and combines them into a risk score used within a conformal calibration framework to decide whether to accept the answer or escalate retrieval. Evaluated on HotpotQA, SAFE-R2R achieves performance comparable to strong retrieval baselines while reducing token usage and unnecessary retrieval through adaptive, risk-aware inference.

Download

Share

COinS