Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG
This addresses the issue of resolving epistemic uncertainty in knowledge-intensive RAG applications, representing a novel paradigm shift rather than an incremental improvement.
The paper tackles the problem of insufficient evidence selection in Retrieval-Augmented Generation (RAG) systems under uncertainty by introducing Entropic Claim Resolution (ECR), an algorithm that reframes reasoning as entropy minimization and dynamically selects evidence to achieve epistemic sufficiency.
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.