Skip to content

STAR: Structure-Aware Adaptive Retrieval for RAG

· 0 citations · 19 references

TL;DR

STAR is presented, a structure-aware adaptive retrieval framework for RAG that treats this mismatch as a problem of diagnosing evidence sufficiency and benefits from a control signal that preserves structurally distinct insufficiency patterns rather than collapsing them into a single scalar confidence estimate.

View source

Similar papers

Preprint Aug 2026

Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG

Making retrieval evaluation more closely reflect the evidence needed for generation does not by itself make every downstream use of that evaluation more reliable, and RAG evaluation methods should be assessed with respect to the particular comparisons, decisions, and conclusions they are intended to support.

Utshab Kumar Ghosh, D. Mukhopadhyay, Shubham Chatterjee · 0 citations
Preprint Aug 2026

The RAT: A Unified Bayesian Model for RAG Evaluation

A Bayesian evaluation framework is introduced that jointly models retrieval success, abstention behavior, and answer correctness, factorized according to the pipeline's information flow, and extends to incorporate LLM-as-a-judge annotations as calibrated noisy observations, enabling practitioners to combine limited hum...

Pius von Däniken, Felix Matthias Saaro, Mark Cieliebak et al. · 0 citations
Preprint Oct 2026

CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG

Multimodal RAG retrieves text, tables, images, and videos, but choosing a retrieval granularity does not determine how much context to retain within each item. Coarse units include irrelevant content, while uniformly fine selection can remove context needed to interpret the evidence. Existing compressors address this t...

Hyojeong Yun, Jueun Kim, Wook-Shin Han · 0 citations
Preprint Aug 2026

Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval

This work proposes Factorized Hypothesis Search (FHS), which maintains multiple partial interpretations over named semantic dimensions that support structured query rendering, multi-hypothesis retrieval, and dimension-level candidate verification.

Lin-Hai Ma, Ethan F. Wei, Xue-Qing Peng et al. · 0 citations
Conference Open access Sep 2026

Your Retriever Already Knows: Predicting RAG Retrieval Sufficiency from Score Distributions

Standard Retrieval-Augmented Generation (RAG) pipelines often provide no reliable inference-time signal of whether retrieval succeeded; on ambiguous or out-of-scope queries, generation may then hallucinate. Motivated by a Czech nuclear-regulator deployment where data sensitivity precludes third-party LLM APIs, we compa...

Matyáš Veselý, M. Prusek, Jirí Franc · 1 citation
#artificial intelligence Preprint Sep 2026

BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence

BELIEFRAG is introduced, a closed-loop controller that updates an explicit state over sufficiency, reliability, conflict, uncertainty, evidence gaps, and acquisition cost, then chooses among retrieval, query rewriting, verification, answering, stopping, and abstention.

Hong-Ji Pu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.