Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering

• URL: http://arxiv.org/abs/2602.06050v1
• Date: Wed, 14 Jan 2026 04:08:31 GMT
• Title: Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering
• Authors: Jongha Kim, Byungoh Ko, Jeehye Na, Jinsung Yoon, Hyunwoo J. Kim,
• Abstract summary: Relevance-aware Multi-context Contrastive Decoding (RMCD) is a novel decoding method for RAG.<n>RMCD outputs a final prediction by combining outputs predicted with each context, where each output is weighted based on its relevance to the question.<n>Experiments show that RMCD consistently outperforms other decoding methods across multiple LVLMs.
• Score: 37.441396497173265
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the remarkable capabilities of Large Vision Language Models (LVLMs), they still lack detailed knowledge about specific entities. Retrieval-augmented Generation (RAG) is a widely adopted solution that enhances LVLMs by providing additional contexts from an external Knowledge Base. However, we observe that previous decoding methods for RAG are sub-optimal as they fail to sufficiently leverage multiple relevant contexts and suppress the negative effects of irrelevant contexts. To this end, we propose Relevance-aware Multi-context Contrastive Decoding (RMCD), a novel decoding method for RAG. RMCD outputs a final prediction by combining outputs predicted with each context, where each output is weighted based on its relevance to the question. By doing so, RMCD effectively aggregates useful information from multiple relevant contexts while also counteracting the negative effects of irrelevant ones. Experiments show that RMCD consistently outperforms other decoding methods across multiple LVLMs, achieving the best performance on three knowledge-intensive visual question-answering benchmarks. Also, RMCD can be simply applied by replacing the decoding method of LVLMs without additional training. Analyses also show that RMCD is robust to the retrieval results, consistently performing the best across the weakest to the strongest retrieval results. Code is available at https://github.com/mlvlab/RMCD.

Related papers

• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding [56.45689495743107]
  Vgent is a graph-based retrieval-reasoning-augmented generation framework to enhance LVLMs for long video understanding.<n>We evaluate our framework with various open-source LVLMs on three long-video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-15T19:14:58Z)
• REFRAG: Rethinking RAG based Decoding [67.4862300145604]
  REFRAG is an efficient decoding framework that compresses, senses, and expands to improve latency in RAG applications.<n>We provide rigorous validation of REFRAG across diverse long-context tasks, including RAG, multi-turn conversations, and long document summarization.
  arXiv  Detail & Related papers  (2025-09-01T03:31:44Z)
• Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger [51.01841635655944]
  Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks.<n>Existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge.<n>We propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method.
  arXiv  Detail & Related papers  (2025-06-09T14:00:57Z)
• Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding [71.01099784480597]
  Large language models (LLMs) excel at a range of tasks through in-context learning (ICL)<n>We introduce In-Context Contrastive Decoding (ICCD), a novel method that emphasizes input-label mapping.
  arXiv  Detail & Related papers  (2025-02-19T14:04:46Z)
• Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks [11.053340674721005]
  Retrieval-augmented generation (RAG) has gained traction as a powerful approach for enhancing language models by integrating external knowledge sources.<n>This paper proposes an alternative paradigm, cache-augmented generation (CAG) that bypasses real-time retrieval.
  arXiv  Detail & Related papers  (2024-12-20T06:58:32Z)
• Multi-Granularity Guided Fusion-in-Decoder [7.87348193562399]
  We propose the Multi-Granularity guided Fusion-in-Decoder (MGFiD) to discerning evidence across multiple levels of granularity. Based on multi-task learning, MGFiD harmonizes passage re-ranking with sentence classification. It improves decoding efficiency by reusing the results of passage re-ranking for passage pruning.
  arXiv  Detail & Related papers  (2024-04-03T08:56:00Z)

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.