MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware

• URL: http://arxiv.org/abs/2607.28006v1
• Date: Thu, 30 Jul 2026 10:54:09 GMT
• Title: MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware
• Abstract summary: We introduce MMLDSum-Bench, a high-quality benchmark for multimodal long-document summarization.<n>We also propose MMLDSum-LLM, a reproducible two-stage training framework.<n>Our approach significantly improves key-information coverage and cross-modal consistency.
• Score: 11.787892687988368
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal long documents are core carriers of professional knowledge, where critical evidence is sparsely distributed across paragraphs and modalities. This easily causes key information omission and cross-modal hallucinations in summarization by multimodal LLMs. These issues stem from attention drift in long-range dependency modeling and gaps in inter-modal alignment. To address this, we introduce MMLDSum-Bench, a high-quality benchmark for multimodal long-document summarization, covering multiple domains, context-length scales, and visual-textual modality distributions. We further propose MMLDSum-LLM, a reproducible two-stage training framework that combines supervised fine-tuning with visual-alignment weighted loss and keyword-aware weighted loss, followed by GRPO with a multi-objective reward (keyword coverage, image-text alignment, ROUGE, and length control). Extensive experiments on MMLDSum-Bench, comparing against leading closed-source and open-source multimodal models under a unified evaluation protocol - including LLM-as-a-judge scoring, atomic-claim precision/recall, image-text alignment (ITA), and ROUGE - demonstrate that our approach significantly improves key-information coverage and cross-modal consistency.

Related papers

• MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios [44.67920911003142]
  We introduce MMLongEmbed, the first comprehensive benchmark for evaluating MEMs in long-context scenarios.<n> MMLongEmbed comprises four retrieval tasks spanning multiple context-length ranges, covering text, document, and video modalities.
  arXiv  Detail & Related papers  (2026-06-05T05:42:34Z)
• HAVEN: Hierarchically Aligned Multimodal Benchmark for Unified Video Understanding [1.8482679687103294]
  HAVEN is a hierarchically aligned multimodal benchmark for unified video understanding.<n>Built upon this unified annotation paradigm, we propose a comprehensive evaluation suite spanning summarization, temporal reasoning, multimodal grounding, and saliency ranking.
  arXiv  Detail & Related papers  (2026-05-19T00:48:14Z)
• PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging [80.17966517536102]
  We argue that the core of Multimodal Large Language Models pre-training lies in establishing effective cross-modal alignment.<n>Motivated by this insight, we introduce the post-alignment merging task, which aims to integrate cross-modal alignment capabilities learned from multimodal pre-training.<n>We propose PivotMerge, a post-alignment merging framework for cross-modal projectors.
  arXiv  Detail & Related papers  (2026-04-18T09:38:03Z)
• Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval [27.493644447594367]
  MCMR (Multi-Conditional Multimodal Retrieval) is a large-scale benchmark designed to evaluate fine-grained, multi-condition cross-modal retrieval under natural-language queries.<n>It spans five product domains: upper and bottom clothing, jewelry, shoes, and furniture.<n>We benchmark a diverse suite of MLLM-based multimodal retrievers and vision-language rerankers to assess their condition-aware reasoning abilities.
  arXiv  Detail & Related papers  (2026-03-01T12:53:47Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering [60.062194349648195]
  Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents.<n>Current document retrieval-augmented generation (DocRAG) methods remain limited by their text-centric approaches.<n>We introduce MMDocRAG, a comprehensive benchmark featuring 4,055 expert-annotated QA pairs with multi-page, cross-modal evidence chains.
  arXiv  Detail & Related papers  (2025-05-22T09:52:57Z)
• MCiteBench: A Multimodal Benchmark for Generating Text with Citations [31.793037002996257]
  Multimodal Large Language Models (MLLMs) have advanced in integrating diverse modalities but frequently suffer from hallucination.<n>Existing work primarily focuses on generating citations for text-only content, leaving the challenges of multimodal scenarios largely unexplored.<n>We introduce MCiteBench, the first benchmark designed to assess the ability of MLLMs to generate text with citations in multimodal contexts.
  arXiv  Detail & Related papers  (2025-03-04T13:12:39Z)
• Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts [56.7225771305861]
  This paper introduces Multi-Modal Retrieval-Augmented Generation (M$2$RAG), a benchmark designed to evaluate the effectiveness of Multi-modal Large Language Models.<n>The benchmark comprises four tasks: image captioning, multi-modal question answering, multi-modal fact verification, and image reranking.<n>To enhance the context utilization capabilities of MLLMs, we also introduce Multi-Modal Retrieval-Augmented Instruction Tuning (MM-RAIT)
  arXiv  Detail & Related papers  (2025-02-24T16:25:25Z)
• VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation [100.06122876025063]
  This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings.<n>We propose VisDoMRAG, a novel multimodal Retrieval Augmented Generation (RAG) approach that simultaneously utilizes visual and textual RAG.
  arXiv  Detail & Related papers  (2024-12-14T06:24:55Z)
• Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
  Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
  arXiv  Detail & Related papers  (2024-02-19T14:59:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.