ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval

• URL: http://arxiv.org/abs/2606.20280v1
• Date: Thu, 18 Jun 2026 14:23:23 GMT
• Title: ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
• Abstract summary: Grain blindness refers to the tendency of the model to overlook grain-level information contained in the query.<n>We introduce ELVA, a novel rule-based RL framework that mitigates grain blindness through ranking-driven MLLMs.
• Score: 32.98798778543091
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR). However, previous works have ignored the grain blindness when adapting the contrastive paradigm into retrieval tasks. Grain blindness refers to the tendency of the model to overlook grain-level information contained in the query, which is crucial for effectively handling complex queries. This stems from contrastive learning treating samples as a binary classification (positive/negative), while ignoring the different information carried by each negative sample. To address this, we argue that negatives should be treated differently according to their similarity to the positive sample, enabling the model to learn distinct grain information from each negative. In this paper, we introduce a simple but effective framework, called ELVA, a novel rule-based RL framework that mitigates grain blindness through ranking-driven MLLMs. 1) Instead of relying on reward models, we extend Reinforcement Learning with Verifiable Rewards (RLVR) to retrieval tasks, allowing the model to explore new ranking behaviors without explicit ranking labels. 2) By utilizing rule-based rewards, our approach jointly optimizes the ranking of negative samples while enlarging the similarity gap between positive and negative. To more precisely measure grain blindness, we further introduce MRBench, a new benchmark specifically designed for multi-grain query scenarios. ELVA achieves state-of-the-art results across standard retrieval benchmarks, and its notable 13.1% improvement on MRBench further demonstrates its effectiveness in alleviating grain blindness.

Related papers

• What Works for 'Lost-in-the-Middle' in LLMs? A Study on GM-Extract and Mitigations [1.2879523047871226]
  GM-Extract is a novel benchmark dataset meticulously designed to evaluate LLM performance on retrieval of control variables.<n>We conduct a systematic evaluation of 7-8B parameter models on two multi-document tasks (key-value extraction and question-answering)<n>While a distinct U-shaped curve was not consistently observed, our analysis reveals a clear pattern of performance across models.
  arXiv  Detail & Related papers  (2025-11-17T20:50:50Z)
• UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning [101.62386137855704]
  We present a novel Universal Multimodal Embedding (UniME-V2) model.<n>Our approach first constructs a potential hard negative set through global retrieval.<n>We then introduce the MLLM-as-a-Judge mechanism, which utilizes MLLMs to assess the semantic alignment of query-candidate pairs.<n>These scores serve as a foundation for hard negative mining, mitigating the impact of false negatives and enabling the identification of diverse, high-quality hard negatives.
  arXiv  Detail & Related papers  (2025-10-15T13:07:00Z)
• LLM Routing with Dueling Feedback [49.67815163970033]
  We study the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost.<n>We formulate routing as contextual dueling bandits, learning from pairwise preference feedback rather than absolute scores.<n>We introduce Category-Calibrated Fine-Tuning (CCFT), a representation-learning method that derives model embeddings from offline data using contrastive fine-tuning with categorical weighting.
  arXiv  Detail & Related papers  (2025-10-01T12:52:25Z)
• UniMLR: Modeling Implicit Class Significance for Multi-Label Ranking [1.2366208723499548]
  We propose UniMLR, a new MLR paradigm that models implicit class relevance/significance values as probability distributions using the ranking among positive labels.<n>We statistically demonstrate that our method accurately learns a representation of the positive rank order, which is consistent with the ground truth and proportional to the underlying significance values.
  arXiv  Detail & Related papers  (2025-08-29T16:44:50Z)
• LGAI-EMBEDDING-Preview Technical Report [41.68404082385825]
  This report presents a unified instruction-based framework for learning generalized text embeddings optimized for both information retrieval (IR) and non-IR tasks.<n>Our approach combines in-context learning, soft supervision, and adaptive hard-negative mining to generate context-aware embeddings.<n>Results show that our method achieves strong generalization and ranks among the top-performing models by Borda score.
  arXiv  Detail & Related papers  (2025-06-09T05:30:35Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)
• Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification [1.292108130501585]
  We propose a clustering-driven feature fine-tuning method (HC-FT) to enhance the performance of multiple instance learning. The proposed method is evaluated on both CAMELYON16 and BRACS datasets, achieving an AUC of 97.13% and 85.85%, respectively.
  arXiv  Detail & Related papers  (2024-06-02T08:53:45Z)
• Automated Multi-level Preference for MLLMs [41.72392895643214]
  Current multimodal Large Language Models (MLLMs) suffer from hallucination'' One promising path is to utilize reinforcement learning from human feedback (RLHF), which steers MLLMs towards learning superior responses while avoiding inferior ones. We rethink the common practice of using binary preferences (i.e., superior, inferior), and find that adopting multi-level preferences is better for two benefits.
  arXiv  Detail & Related papers  (2024-05-18T03:49:37Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Solving Inefficiency of Self-supervised Representation Learning [87.30876679780532]
  Existing contrastive learning methods suffer from very low learning efficiency. Under-clustering and over-clustering problems are major obstacles to learning efficiency. We propose a novel self-supervised learning framework using a median triplet loss.
  arXiv  Detail & Related papers  (2021-04-18T07:47:10Z)
• Doubly Contrastive Deep Clustering [135.7001508427597]
  We present a novel Doubly Contrastive Deep Clustering (DCDC) framework, which constructs contrastive loss over both sample and class views. Specifically, for the sample view, we set the class distribution of the original sample and its augmented version as positive sample pairs. For the class view, we build the positive and negative pairs from the sample distribution of the class. In this way, two contrastive losses successfully constrain the clustering results of mini-batch samples in both sample and class level.
  arXiv  Detail & Related papers  (2021-03-09T15:15:32Z)

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.