Challenge: Existing benchmarks for document QA for visually rich documents outperform unimodal and long-context LLMs by 12-20%.
Approach: They propose a multimodal Retrieval Augmented Generation approach that integrates visual and textual retrieval with linguistic reasoning.
Outcome: The proposed approach outperforms unimodal and long-context LLM benchmarks for document QA by 12-20%.

Similar Papers

ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on textual data, single-document comprehension, or evaluating retrieval and generation in isolation.
Approach: They propose a multimodal RAG benchmark featuring multi-type queries over visually rich document corpora.
Outcome: The proposed benchmark outperforms existing benchmarks in visual retrieval and human-verified queries.
ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks focus on image-based question answering (QA) but ignore the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents.
Approach: They propose a novel multi-agent RAG framework tailored for complex reasoning across visual documents that employs a Gaussian Mixture Model (GMM)-based hybrid strategy to handle multi-modal retrieval.
Outcome: The proposed framework outperforms existing methods by over 10% on the competitive ViDoSeek benchmark.
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for Knowledge-Based Visual Question Answering lack multimodal retrieval . large language models (LLMs) have demonstrated remarkable generalization and reasoning capabilities in text-based systems.
Approach: They propose a multimodal vision-language retrieval-augmented generation system that harmonizes multiple modalities and modality to enhance retrieval.
Outcome: The proposed system achieves state-of-the-art retrieval performance and competitive answers on InfoSeek and Encyclopedic-VQA benchmarks.
MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing RAG solutions for large language models are limited by context windows limiting their ability to process long-form, domain-specific content.
Approach: They propose a multimodal knowledge graph-based RAG that enables cross-modal reasoning . their method incorporates visual cues into the construction of knowledge graphs, retrieval phase, and answer generation process .
Outcome: Experimental results show that the proposed approach outperforms existing approaches on textual and multimodal benchmarks.
FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for retrieval-augmented generation are inefficient and often fail to maintain high answer quality.
Approach: They propose an efficient VLM-based RAG framework built on a speculative decoding pipeline and a similarity-based filtering strategy to mitigate errors.
Outcome: The proposed framework reduces inference latency without sacrificing correctness . it achieves comparable or higher accuracy than standard approaches while speeding up inference by approximately 2x .
T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation (2026.eacl-long)

Copied to clipboard

Challenge: Existing QA datasets containing text-and-table data typically contain context-dependent questions, which may yield multiple correct answers depending on the provided context.
Approach: They propose a benchmark to evaluate RAG methods on text-and-table data.
Outcome: The proposed method evaluates RAG methods on real-world text-and-table data.
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A (2026.acl-industry)

Copied to clipboard

Challenge: Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and answer generation.
Approach: They propose a document structure-aware split that extracts and represents document structure via a structure-based split that dynamically routes documents through orientation-specific ingestion pipelines.
Outcome: The proposed model outperforms state-of-the-art vision-centric baselines by up to 32% points and achieves strong gains on report-style layouts.
Federated Retrieval Augmented Generation for Multi-Product Question Answering (2025.coling-industry)

Copied to clipboard

Challenge: Existing multi-domain RAG-QA approaches query all domains indiscriminately or rely on rigid resource selection.
Approach: They propose a multi-product knowledge-augmented QA framework with probabilistic federated search across domains and relevant knowledge.
Outcome: The proposed framework improves multi-product knowledge-augmented QA performance on Adobe products.
Benchmarking Retrieval-Augmented Generation for Medicine (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have state-of-the-art performance on a wide range of medical question answering tasks, but they still face challenges with hallucinations and outdated knowledge.
Approach: They propose a benchmark to evaluate medical RAG systems using large-scale experiments with over 1.8 trillion prompt tokens.
Outcome: The proposed benchmark improves accuracy of six different LLMs by up to 18% over chain-of-thought prompting.
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to retrievalaugmented generation (RAG) are limited when applied to heterogeneous documents . flattening tables and chunking strategies disrupt tabular structure, leads to information loss, and undermines reasoning capabilities of LLMs in multi-hop, global queries.
Approach: They propose a SQL-based framework that unifies textual understanding and complex manipulations over tabular data.
Outcome: The proposed framework outperforms baselines on public datasets and HeteQA on heterogeneous document question answering.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations