Read Together, Answer Apart: How Earlier Questions Help Vision-Language Models Look
Xinyi Guo, Kaile Huang, Xitong Ling, Mingyi He, Chende Zheng, Jianyu Xu, Chao He, Dongqing Song
原文摘要
Vision-language models (VLMs) are often asked several questions about the same image in a single prompt (co-asking), yet existing evaluations report conflicting accuracy gains and hallucinations at the prompt level without tracking how individual answers change. By pairing each question's single-question and co-asked answers across 22 open-weight VLMs (1B-35B), we find that erratic net shifts reflect two opposing effects: on Densely Captioned Images (DCI), every model repairs 15.4%-29.8% of its single-question errors under co-asking, while the share of correct answers turned wrong falls from 30.8% on weaker models to 4.7% on stronger ones. Across all 14 models supporting custom attention masks, we show through attention readouts and layer-window interventions that earlier same-image questions read visual information into their question tokens in the early-to-middle layers during prefill, helping later questions concentrate image attention onto their queried targets. This visual help accumulates across the scene even across non-overlapping regions, whereas blocking earlier questions from attending to the image lowers both target localization and accuracy in all 14 models. While cross-question help is established during shared question reading, part of the co-asking damage enters later during answer decoding when the decoder attends to other question stems. We therefore introduce Read Together, Answer Apart, a training-free decoding mask that keeps shared prefill intact and isolates each answer from other stems, improving co-asking accuracy on 12 of 14 models on DCI (up to +4.71 percentage points, closing 70% of the pooled gap to asking alone) and on 10, 8, and 5 of the 14 models on WebUI, FinTabNet, and GQA (up to +11.4, +5.3, and +1.1 points).
cs.CV