TestHallVQA: חקירת רישום-שפה גדול-מבט-מודלים תחת מצבי תיעוד-שוליים מבחני מדע

תקציר מקורי באנגליתarXiv:2609.13158v1 Announce Type: new Abstract: Large Vision--Language Models (LVLMs) are increasingly expected to perform visual question answering (VQA) over planar media. However, existing planar VQA benchmarks typically emphasize isolated challenges: some emphasize long-document understanding with limited reasoning depth, while others require complex visual reasoning but remain restricted to single-page, noise-free settings. Moreover, through theoretical analysis, we identify the impact of irrelevant visual tokens, which leads to measurable performance degradation but has received little attention with respect to systematic quantification. To address these limitations, we introduce TestHallVQA, a multi-image VQA benchmark that simultaneously embodies document-level scale and the diffic