Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG

• URL: http://arxiv.org/abs/2607.05438v1
• Date: Fri, 03 Jul 2026 15:28:16 GMT
• Title: Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG
• Abstract summary: We show that the relevance of a modality to a question is a weak predictor of whether that modality is actually needed to answer correctly.<n>We propose textbfpost-hoc selective modality escalation: answer cheaply from text and tables, run a verifier, and pay for VLM evidence only there.
• Score: 7.082282444371973
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal retrieval-augmented generation (RAG) grounds a generator in evidence drawn from heterogeneous modalities -- text, tables, and images. The dominant deployment choice is binary and made before the model has tried to answer: either run a cheap text(+table) pipeline, or pay for an expensive vision-language model (VLM) over every image. Recent adaptive systems improve on this by selecting the modality or fidelity pre-retrieval, from a question-conditioned predictor of which modality will be needed. We show that this is the wrong decision point. Through an oracle headroom analysis on MultiModalQA, we find that the relevance of a modality to a question is a weak predictor of whether that modality is actually needed to answer correctly: a large fraction of questions whose gold support includes an image are nonetheless answerable from text and tables alone, and a pre-retrieval router that escalates on apparent visual relevance over-escalates substantially relative to an oracle. We propose \textbf{post-hoc selective modality escalation}: answer cheaply from text and tables, run a verifier on the (query, draft answer, evidence) tuple that localizes which modality is missing, and pay for VLM evidence only there. A calibrated value-of-escalation router then decides whether the expected accuracy gain justifies the visual cost. On MultiModalQA, our router recovers the accuracy of an always-on VLM pipeline while issuing far fewer visual calls, and closes most of the gap to the oracle escalation rate. The result extends a routing-signal hierarchy established for retrieval depth and reasoning hops to a third axis -- modality -- under a single cost-aware selective-escalation view.

Related papers

• A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification [0.18427704077999105]
  We propose a generative AI integrated multimodal ReID framework designed explicitly for robustness under missing cues and low latency deployment.<n>We report person re-identification performance using mAP and Rank-1 accuracy on the Market-1501 and DukeMTMC-reID benchmarks.
  arXiv  Detail & Related papers  (2026-09-13T10:40:38Z)
• Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning [72.45536737928015]
  We propose Switch-Reasoner, a framework that learns to adaptively select reasoning modes for MLLMs.<n>It treats thinking as a virtual tool invocation and allows the model to either answer directly or invoke explicit reasoning before answering.<n>Experiments on 11 multimodal tasks show that Switch-Reasoner reduces unnecessary reasoning while maintaining strong performance.
  arXiv  Detail & Related papers  (2026-07-09T15:04:05Z)
• Constrained Dominant Sets for Multimodal Document Question Answering [6.071121358322323]
  Long multimodal document question answering is limited by which evidence reaches the reader, rather than by the quantity retrieved.<n>This work introduces a retriever that selects evidence as a Constrained Dominant Set on a query-augmented affinity graph.
  arXiv  Detail & Related papers  (2026-06-05T13:24:46Z)
• Uncertainty Quantification for Multimodal Retrieval Augmented Generation [14.789439938448034]
  We show that modeling uncertainty using multimodal and retrieval-aware probability signals improves estimation in multimodal RAG systems.<n>Our proposed LeMUQ increases the AUROC metric by 3.8% on average.<n>Our findings highlight the importance of modeling multimodal uncertainty and provide a step toward more reliable and safer multimodal RAG systems.
  arXiv  Detail & Related papers  (2026-05-28T14:00:32Z)
• LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer? [69.71754384259167]
  Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency.<n>We propose Latent, a router that formulates MLLM routing as counterfactual multimodal utility prediction.<n> Experiments on MMR-Bench and VL-Bench show that Latent outperforms fixed-model, feature-level, and learned-router baselines.
  arXiv  Detail & Related papers  (2026-05-11T22:42:12Z)
• Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection [57.3886742625188]
  Pre-Route is a proactive routing framework that performs structured reasoning before answering.<n>Our study shows three key findings: (i) LLMs possess latent routing ability that can be reliably elicited with guidelines; (ii) linear probes reveal that structured prompts sharpen the separability of the "optimal routing" in representation space; and (iii) distillation transfers this reasoning structure to smaller models for lightweight deployment.
  arXiv  Detail & Related papers  (2026-05-11T09:10:55Z)
• DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification [38.65432183778467]
  We introduce DeltaRubric, an approach that reformulates multimodal preference evaluation as a plan-and-execute process within a single MLLM.<n>DeltaRubric operates in two steps: acting first as a $textitDisagreement Planner$, it generates a neutral, instance-specific verification checklist.<n>We formulate DeltaRubric as a multi-role reinforcement learning problem, jointly optimizing planning and verification capabilities.
  arXiv  Detail & Related papers  (2026-05-10T02:32:19Z)
• Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models [58.46663983451155]
  PixSearch is an end-to-end Segmenting Large Multimodal Model (LMM) that unifies region-level perception and retrieval-augmented reasoning.<n>During encoding, PixSearch emits search> tokens to trigger retrieval, selects query modalities (text, image, or region), and generates pixel-level masks that directly serve as visual queries.<n>On egocentric and entity-centric VQA benchmarks, PixSearch substantially improves factual consistency and generalization.
  arXiv  Detail & Related papers  (2026-01-27T00:46:08Z)
• 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)
• ManyModalQA: Modality Disambiguation and QA over Diverse Inputs [73.93607719921945]
  We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities. We collect our data by scraping Wikipedia and then utilize crowdsourcing to collect question-answer pairs.
  arXiv  Detail & Related papers  (2020-01-22T14:39:28Z)

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.