SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
This addresses a critical reliability issue in MLLMs for applications like image captioning and visual QA, though it is an incremental improvement over existing training-free methods.
The paper tackles object hallucination in Multimodal Large Language Models (MLLMs) by proposing SAVE, a framework that uses Sparse Autoencoder features to enhance visual information, resulting in a 10% improvement in CHAIR_S and gains on other benchmarks.
Although Multimodal Large Language Models (MLLMs) have advanced substantially, they remain vulnerable to object hallucination caused by language priors and visual information loss. To address this, we propose SAVE (Sparse Autoencoder-Driven Visual Information Enhancement), a framework that mitigates hallucination by steering the model along Sparse Autoencoder (SAE) latent features. A binary object-presence question-answering probe identifies the SAE features most indicative of the model's visual information processing, referred to as visual understanding features. Steering the model along these identified features reinforces grounded visual understanding and effectively reduces hallucination. With its simple design, SAVE outperforms state-of-the-art training-free methods on standard benchmarks, achieving a 10\%p improvement in CHAIR\_S and consistent gains on POPE and MMHal-Bench. Extensive evaluations across multiple models and layers confirm the robustness and generalizability of our approach. Further analysis reveals that steering along visual understanding features suppresses the generation of uncertain object tokens and increases attention to image tokens, mitigating hallucination. Code is released at https://github.com/wiarae/SAVE.