Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning
This addresses reliability issues in multimodal AI systems for applications like visual question answering, though it is incremental as it builds on existing Retrieval Augmented Generation frameworks.
The paper tackled the problem of hallucinations in Visual Question Answering systems by proposing Multimodal Adaptive RAG (MMA-RAG), which dynamically decides when to use retrieved external knowledge based on internal model confidence, resulting in significant performance improvements across three VQA datasets.
Visual Question Answering systems face reliability issues due to hallucinations, where models generate answers misaligned with visual input or factual knowledge. While Retrieval Augmented Generation frameworks mitigate this issue by incorporating external knowledge, static retrieval often introduces irrelevant or conflicting content, particularly in visual RAG settings where visually similar but semantically incorrect evidence may be retrieved. To address this, we propose Multimodal Adaptive RAG (MMA-RAG), which dynamically assesses the confidence in the internal knowledge of the model to decide whether to incorporate the retrieved external information into the generation process. Central to MMA-RAG is a decision classifier trained through a layer-wise analysis, which leverages joint internal visual and textual representations to guide the use of reverse image retrieval. Experiments demonstrated that the model achieves a significant improvement in response performance in three VQA datasets. Meanwhile, ablation studies highlighted the importance of internal representations in adaptive retrieval decisions. In general, the experimental results demonstrated that MMA-RAG effectively balances external knowledge utilization and inference robustness in diverse multimodal scenarios.