arXiv Computation and Language September 1, 2026 By Jueun Kim, Sungho Park, Wook-Shin Han

Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering

Read the original on arXiv Computation and Language →

Hi-Q is a new framework for multi‑hop question answering that refines queries hierarchically based on evidence retrieved from a corpus. At each node it tests whether the current query unit is supported by evidence; if not, the node is expanded using a dependency‑preserving binary operator and verified for semantic coverage. The resulting query tree grows according to corpus support signals, and Hi‑Q achieves state‑of‑the‑art performance on three multi‑hop QA benchmarks, outperforming both iterative retrieval and graph‑based baselines without constructing a corpus‑wide graph.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jul 28

HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering

arXiv:2607. 22597v1 Announce Type: new Abstract: Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process.

By Hong-Yu An, Yun-Jian Zhang, Chen-Wei Liang, Tian-Yi Zhang, Jian Ding, Yi-Lun Wu, Ao-Bo Li, Wei-Cong Su, Saifullah, Mujiangshan Wang

llms rag nlp

arXiv AI

Jun 30

Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

arXiv:2606. 30133v1 Announce Type: cross Abstract: Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging graph structure.

By Illia Makarov, Mykola Glybovets

rag diffusion nlp benchmarks

arXiv AI

Sep 1

PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation

arXiv:2608.29753v1 Announce Type: new Abstract: Multi-hop question answering in retrieval-augmented gener?ation (RAG) often benefits from retrieving beyond the few candidates that will finally be rea...

By Haokun Deng, Xunkai Li, Hongchao Qin, Rong-Hua Li

rag nlp benchmarks

arXiv AI

Sep 10

Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval

arXiv:2609.07050v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularl...

By JungMin Yun, YoungBin Kim

rag nlp

arXiv AI

Jun 4

QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples

arXiv:2606. 04646v1 Announce Type: cross Abstract: Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text.

By Mengao Zhang, Xiang Yang, Chang Liu, Tianhui Tan, Ke-wei Huang

llms rag nlp benchmarks data-engineering

arXiv AI

Sep 12

MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG

MOSAIC is a training‑free framework that adapts Graph Retrieval‑Augmented Generation (GraphRAG) to each query by converting query‑specific evidence needs into a bounded policy over seed selection, traversal, stopping, and evidence selection. It keeps the corpus graph, indexes, scoring, grounding, and answer generation shared, while an LLM analyzer tailors the exploration strategy per query. On GraphRAG‑Bench, MOSAIC improves answer correctness by over 5 points on Medical and 4 points on Novel, achieves high evidence recall and context relevancy, and reduces path and evidence evaluations compared to fixed policies.

By EunKyeong Lee, Kyeong-Jin Oh, Jinwon Kim, Hye Woo Lee, Minsang Song, Hyeongjun Jang, Junyoung Youn

llms rag benchmarks

One email a morning, machine-written

Related stories

HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering

Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation

Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval

QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples

MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG