Understanding the Effects of Distractors on Reasoning Vision-Language Models
Quick summary
arXiv:2511.21397v3 Announce Type: replace-cross Abstract: How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)? Prior work on text-only language models has shown that textual distractors can intensify inverse scaling, causing models to reason longer but less effective reasoning traces. In this work, we investigate whether similar phenomena arise in multimodal settings. We introduce Idis (Images with distractors), a visual question-answering dataset that systematically varies distractors along semantic and numerical dimensions. Our analys
Key takeaways
- arXiv:2511.21397v3 Announce Type: replace-cross Abstract: How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)?
- Prior work on text-only language models has shown that textual distractors can intensify inverse scaling, causing models to reason longer but less effective reasoning traces.
- In this work, we investigate whether similar phenomena arise in multimodal settings.
Why it matters
“Understanding the Effects of Distractors on Reasoning Vision-Language Models” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments