Aug 2026· 2026 3rd International Conference on Intelligent Systems and Robotics (CISR)· pp. 1-7· 0 citations· 17 references
Abstract
Retrieval-Augmented Generation (RAG) systems typically apply identical retrieval logic to all user queries, overlooking that different query intents depend on fundamentally different document relationships. We propose QMEG, a query-aware retrieval framework that constructs a multi-relational evidence graph with five active semantic edge types (plus one reserved for future borrowing data) and dynamically activates edge subsets according to query intent. On a library dataset of 19,818 books with 250 annotated queries, QMEG achieves 31% higher diversity on learningpath queries and 47% higher LLM-judged quality on fact queries compared to fixed-graph baselines, while remaining robust under weight perturbation. Ablation reveals that the topic-similarity edge is indispensable for exploratory recommendation, with diversity dropping 34% upon its removal.
LiteRAG is presented, a graph-based retrieval method that replaces expensive retrieval-time LLM control with query-conditioned algorithmic exploration and reasoning-chain context construction and attains the highest overall quality among the evaluated methods.
Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons· 0 citations
Coherence-Aware Graph Encoding (CAGE) is introduced, a reranking framework that models"between-chunk coherence" across four dimensions: Intra-Domain Relevance, Noise Resistance, Informational Bonding, and Factual Consistency.
Tong Qi, Jing-Yu Wu, Youbing Yin et al.· 0 citations
Mosaic is presented, a training-free framework that formulates GraphRAG retrieval as a per-query control problem that converts query-specific evidence requirements into a bounded policy over seed selection, graph traversal, stopping, and evidence selection while the corpus graph, indexes, scoring functions, grounding p...
Eunkyeong Lee, Kyeong-Jin Oh, Jinwon Kim et al.· 0 citations
Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where heterogeneous queries require different chunking granularities, metadata constraints, and source-se...
Aurélien Pellet, Julien Perez, Marie Puren· 0 citations
Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves retrieval and answer quality. We show that its effectiveness varies primarily with candidate-pool redundancy, in a pattern consistent with the number of distinct evidence p...
Guillaume Brouillette, Faustin Kagabo, Usef Faghihi et al.· 0 citations
Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free graph retrieval methods rely primarily on query-sentence similarity to search for evidence. This can exclude useful bridging evidence with low query similarity and activa...
Ba-Xian Liu, Tong Wei· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
