How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
This work addresses interpretability gaps in LVLMs for researchers and practitioners, though it is incremental as it builds on existing model analysis without introducing a new paradigm.
The paper investigates how large vision-language models (LVLMs) process text in images by identifying specialized 'OCR heads' that are less sparse, qualitatively distinct, and statically activated compared to general retrieval heads, with validation showing performance improvements through redistribution of sink-token values.
Despite significant advancements in Large Vision Language Models (LVLMs), a gap remains, particularly regarding their interpretability and how they locate and interpret textual information within images. In this paper, we explore various LVLMs to identify the specific heads responsible for recognizing text from images, which we term the Optical Character Recognition Head (OCR Head). Our findings regarding these heads are as follows: (1) Less Sparse: Unlike previous retrieval heads, a large number of heads are activated to extract textual information from images. (2) Qualitatively Distinct: OCR heads possess properties that differ significantly from general retrieval heads, exhibiting low similarity in their characteristics. (3) Statically Activated: The frequency of activation for these heads closely aligns with their OCR scores. We validate our findings in downstream tasks by applying Chain-of-Thought (CoT) to both OCR and conventional retrieval heads and by masking these heads. We also demonstrate that redistributing sink-token values within the OCR heads improves performance. These insights provide a deeper understanding of the internal mechanisms LVLMs employ in processing embedded textual information in images.