# Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG

Source: [Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG](<https://www.sota2.com/research/paper/69cb557d0636e5bf4afca3ce>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-01T05:00:20.432Z

Authors: Davide Di Gioia

Published: 2026-03-30T13:49:03.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-Hop Question Answering on HotpotQA 300 Questions (EM, F1, Faithfulness)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-300-questions-em-f1-faithfulness.md>): Multi-hop Question Answering; HotpotQA 300 Questions; Exact Match (EM): 29.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.28444>)

[PDF](<https://arxiv.org/pdf/2603.28444.pdf>)
