Retrieval-augmented in-context learning for multimodal large language models in disease classification

• URL: http://arxiv.org/abs/2505.02087v1
• Date: Sun, 04 May 2025 12:43:56 GMT
• Title: Retrieval-augmented in-context learning for multimodal large language models in disease classification
• Authors: Zaifu Zhan, Shuang Zhou, Xiaoshan Zhou, Yongkang Xiao, Jun Wang, Jiawen Deng, He Zhu, Yu Hou, Rui Zhang,
• Abstract summary: RAICL integrates retrieval-augmented generation (RAG) and in-context learning (ICL) to adaptively select demonstrations with similar disease patterns.<n>We evaluated the framework on two real-world multi-modal datasets.
• Score: 18.48849976529677
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Objectives: We aim to dynamically retrieve informative demonstrations, enhancing in-context learning in multimodal large language models (MLLMs) for disease classification. Methods: We propose a Retrieval-Augmented In-Context Learning (RAICL) framework, which integrates retrieval-augmented generation (RAG) and in-context learning (ICL) to adaptively select demonstrations with similar disease patterns, enabling more effective ICL in MLLMs. Specifically, RAICL examines embeddings from diverse encoders, including ResNet, BERT, BioBERT, and ClinicalBERT, to retrieve appropriate demonstrations, and constructs conversational prompts optimized for ICL. We evaluated the framework on two real-world multi-modal datasets (TCGA and IU Chest X-ray), assessing its performance across multiple MLLMs (Qwen, Llava, Gemma), embedding strategies, similarity metrics, and varying numbers of demonstrations. Results: RAICL consistently improved classification performance. Accuracy increased from 0.7854 to 0.8368 on TCGA and from 0.7924 to 0.8658 on IU Chest X-ray. Multi-modal inputs outperformed single-modal ones, with text-only inputs being stronger than images alone. The richness of information embedded in each modality will determine which embedding model can be used to get better results. Few-shot experiments showed that increasing the number of retrieved examples further enhanced performance. Across different similarity metrics, Euclidean distance achieved the highest accuracy while cosine similarity yielded better macro-F1 scores. RAICL demonstrated consistent improvements across various MLLMs, confirming its robustness and versatility. Conclusions: RAICL provides an efficient and scalable approach to enhance in-context learning in MLLMs for multimodal disease classification.

Related papers

• Large Language Models are Demonstration Pre-Selectors for Themselves [57.101804269100185]
  In-context learning (ICL) with large language models (LLMs) delivers strong few-shot performance by choosing few-shot demonstrations from the entire training data.<n>FEw yet Essential Demonstration prE-selectoR is a novel pre-selection framework that identifies a representative subset of demonstrations.<n>FEw yet Essential Demonstration prE-selectoR can reduce training data size by over 20% while maintaining performance.
  arXiv  Detail & Related papers  (2025-06-06T12:29:03Z)
• QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines [4.94507535566914]
  We show that combining two distinct small language models (SLMs) with different architectures can outperform large language models (LLMs) in relevance assessment.<n>Our approach -- QUPID -- integrates a generative SLM with an embedding-based SLM, achieving higher relevance judgment accuracy.
  arXiv  Detail & Related papers  (2025-05-12T08:35:09Z)
• Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute [54.22256089592864]
  This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute.<n>Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage their complementary strengths.
  arXiv  Detail & Related papers  (2025-04-01T13:13:43Z)
• Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation [61.64052577026623]
  Real-world multi-view datasets are often heterogeneous and imperfect.<n>We propose a novel robust MVL method (namely RML) with simultaneous representation fusion and alignment.<n>In experiments, we employ it in unsupervised multi-view clustering, noise-label classification, and as a plug-and-play module for cross-modal hashing retrieval.
  arXiv  Detail & Related papers  (2025-03-06T07:01:08Z)
• Visual RAG: Expanding MLLM visual knowledge without fine-tuning [5.341192792319891]
  This paper introduces Visual RAG, that synergically combines the MLLMs capability to learn from the context, with a retrieval mechanism.<n>In this way, the resulting system is not limited to the knowledge extracted from the training data, but can be updated rapidly and easily without fine-tuning.<n>It greatly reduces the computational costs for improving the model image classification performance, and augments the model knowledge to new visual domains and tasks it was not trained for.
  arXiv  Detail & Related papers  (2025-01-18T17:43:05Z)
• More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives [50.772462704559345]
  We introduce DrICL, a novel optimization method that enhances model performance through Differentiated Learning and advantage-based Reweighting objectives.<n>Globally, DrICL utilizes differentiated learning to optimize the NLL objective, ensuring that many-shot performance surpasses zero-shot levels.<n>We develop the Many-Shot ICL Benchmark (ICL-50)-a large-scale benchmark of 50 tasks that cover shot numbers from 1 to 350 within sequences of up to 8,000 tokens-for fine-tuning purposes.
  arXiv  Detail & Related papers  (2025-01-07T14:57:08Z)
• Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies [0.9217021281095907]
  This study evaluates the effectiveness of Vision Language Models (VLMs) in representing and utilizing multimodal content for fact-checking.<n>We show that while multimodality can enhance performance, fusing separate embeddings from text and image encoders yielded superior results compared to using VLM embeddings.
  arXiv  Detail & Related papers  (2024-12-06T16:13:19Z)
• Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition [12.382193259575805]
  We propose a novel multi-modality co-learning (MMCL) framework for efficient skeleton-based action recognition. Our MMCL framework engages in multi-modality co-learning during the training stage and keeps efficiency by employing only concise skeletons in inference.
  arXiv  Detail & Related papers  (2024-07-22T15:16:47Z)
• RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition [78.97487780589574]
  Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories. This paper introduces a Retrieving And Ranking augmented method for MLLMs. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base.
  arXiv  Detail & Related papers  (2024-03-20T17:59:55Z)
• Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control [66.78146440275093]
  Learned retrieval (LSR) is a family of neural methods that encode queries and documents into sparse lexical vectors. We explore the application of LSR to the multi-modal domain, with a focus on text-image retrieval. Current approaches like LexLIP and STAIR require complex multi-step training on massive datasets. Our proposed approach efficiently transforms dense vectors from a frozen dense model into sparse lexical vectors.
  arXiv  Detail & Related papers  (2024-02-27T14:21:56Z)
• Extension of Transformational Machine Learning: Classification Problems [0.0]
  This study explores the application and performance of Transformational Machine Learning (TML) in drug discovery. TML, a meta learning algorithm, excels in exploiting common attributes across various domains. The drug discovery process, which is complex and time-consuming, can benefit greatly from the enhanced prediction accuracy.
  arXiv  Detail & Related papers  (2023-08-07T07:34:18Z)
• Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning [104.58874584354787]
  In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models.
  arXiv  Detail & Related papers  (2023-01-27T18:59:01Z)

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.