Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG

TL;DR

The paper introduces Entropic Claim Resolution (ECR), an inference-time algorithm for RAG systems that selects evidence claims by minimizing entropy over competing hypotheses, improving handling of conflicting evidence and ambiguity.

Contribution

ECR is a novel entropy minimization approach for evidence selection in RAG, offering a theoretically grounded, uncertainty-aware alternative to relevance-based retrieval.

Findings

ECR effectively reduces epistemic uncertainty in RAG tasks.

Integration of ECR into CSGR++ improves evidence selection quality.

Theoretical analysis confirms ECR's properties for uncertainty reduction.

Abstract

Current Retrieval-Augmented Generation (RAG) systems predominantly rely on relevance-based dense retrieval, sequentially fetching documents to maximize semantic similarity with the query. However, in knowledge-intensive and real-world scenarios characterized by conflicting evidence or fundamental query ambiguity, relevance alone is insufficient for resolving epistemic uncertainty. We introduce Entropic Claim Resolution (ECR), a novel inference-time algorithm that reframes RAG reasoning as entropy minimization over competing semantic answer hypotheses. Unlike action-driven agentic frameworks (e.g., ReAct) or fixed-pipeline RAG architectures, ECR sequentially selects atomic evidence claims by maximizing Expected Entropy Reduction (EER), a decision-theoretic criterion for the value of information. The process dynamically terminates when the system reaches a mathematically defined state of epistemic sufficiency (H <= epsilon, subject to epistemic coherence). We integrate ECR into a production-grade multi-strategy retrieval pipeline (CSGR++) and analyze its theoretical properties. Our framework provides a rigorous foundation for uncertainty-aware evidence selection, shifting the paradigm from retrieving what is most relevant to retrieving what is most discriminative.