Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation
Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this limitation stems from a representational bottleneck: contrastive 3D CT embeddings encode discriminative pathology signals, yet exhibit severe dimensional concentration, with as few as 2 effective dimensions out of 512. Corroborating this, scaling the language model yields no measurable improvement, suggesting that the bottleneck lies in the visual representation rather than the generator. This bottleneck limits both generation and retrieval; naive static retrieval fails to improve clinical efficacy and can even degrade performance. We propose \textbf{AdaRAG-CT}, an adaptive augmentation framework that compensates for this visual bottleneck by introducing supplementary textual information through controlled retrieval and selectively integrating it during generation. On the CT-RATE benchmark, AdaRAG-CT achieves state-of-the-art clinical efficacy, improving Clinical F1 from 0.420 (CT-Agent) to 0.480 (+6 points); ablation studies confirm that both the retrieval and generation components contribute to the improvement. Code is available at https://github.com/renjie-liang/Adaptive-RAG-for-3DCT-Report-Generation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models
Retrieval-augmented large language models (LLMs) have been remarkably competent in various NLP tasks. However, it was observed by previous works that retrieval is not always helpful, especially when the LLM is already kn…
Continual LearningRetrievalRetrieval-augmented GenerationCiMRAG: CiM-Aware Domain-Adaptive and Noise-Resilient Retrieval-Augmented Generation for Edge-Based LLMs
Personalized virtual assistants powered by large language models (LLMs) on edge devices are attracting growing attention, with Retrieval-Augmented Generation (RAG) emerging as a key method for personalization by retrievi…
Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
Predicting how cells respond to genetic perturbations is fundamental to understanding gene function, disease mechanisms, and therapeutic development. While recent deep learning approaches have shown promise in modeling s…
Text RetrievalBeyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems
The choice of embedding model is a crucial step in the design of Retrieval Augmented Generation (RAG) systems. Given the sheer volume of available options, identifying clusters of similar models streamlines this model se…
Information RetrievalModel SelectionRAGRetrieval+1FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
Small Language Models (SLMs) are attractive for cost-sensitive and resource-limited settings due to their efficient, low-latency inference. However, they often struggle with complex, knowledge-intensive tasks that requir…
Knowledge DistillationLogical Reasoning