arXiv AI August 18, 2026 By Zafar Ali, Asad Khan, Aalia Malik, Pavlos Kefalas

GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG

arXiv:2608. 15056v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation (RAG) systems often rely on long unstructured contexts or aggressively expanded evidence graphs, which can introduce noisy evidence, weaken multi-hop reasoning, and increase unsupported generation.

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 AI.

arXiv AI

Sep 10

CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation

arXiv:2609.05518v1 Announce Type: cross Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, m...

By Jiacheng Cai, Zijin Hong, Zheng Yuan, Huachi Zhou, Qinggang Zhang, Xiao Huang

llms rag multimodal benchmarks

arXiv AI

Sep 1

HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering

arXiv:2608.29088v1 Announce Type: new Abstract: Multimodal question answering remains sensitive to noisy, incomplete, and weakly grounded evidence. Long unstructured contexts can introduce redundancy...

By Zafar Ali, Asad Khan, Nimbeshaho Thierry, Nabila Amir, Adam A. Q. Mohammed, Pavlos Kefalas

llms nlp fine-tuning efficiency multimodal

arXiv AI

Jul 14

MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

arXiv:2604. 04969v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning.

By Sijun Dai, Qiang Huang, Xiaoxing You, Jun Yu

llms rag multimodal benchmarks safety

arXiv AI

Jun 26

MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation

arXiv:2606. 26458v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) over knowledge graphs has emerged as a promising approach for grounding large language models, yet existing benchmarks largely overlook the challenges of retrieval in multimodal knowledge graph RAG (MKG-RAG).

By Xiaochen Wang, Bao Hoang, Han Liu, Ting Wang, Fenglong Ma

llms rag multimodal benchmarks

arXiv AI

Aug 25

SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering

arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visua...

By Long Shu, Shuochen Liu, Wei Chen, Junda Lin, Zhi Zheng, Huijun Hou, Tong Xu

llms nlp reinforcement-learning multimodal benchmarks safety

arXiv AI

Jul 21

ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG

arXiv:2607. 16208v1 Announce Type: new Abstract: Graph-grounded multimodal question answering organizes text, tables, and images in a structured evidence graph, yet end-to-end accuracy depends on which multimodal assets are ranked highly enough to enter downstream reasoning; for graph-linked images, single-vector bi-encoder similarity can discard patch- and token-level structure needed for fine-grained alignment.

By Seonok Kim

nlp multimodal safety

One email a morning, machine-written

Related stories

CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation

HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering

MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation

SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering

ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG