跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-19AI 評分56

視覺語言模型的規模限制:特定子任務出現反向縮放

On the Limits of Scale: Inverse Scaling in Vision-Language Models

AI 導讀

這項研究發現,視覺語言模型在特定子任務上會出現反向縮放,即較大型模型有時不及同系列較小模型。研究評估 19 個模型及 8 個多模態基準,共進行 558,334 次模型與問題評估,找出 375 組出現反向縮放的子任務與模型配對。影響較大的領域包括多圖像空間推理、視覺感知及大學程度 STEM 知識,部分案例準確率差距超過 20 個百分點;圖表理解相對較不受影響。

正文

Published on Oct 19

Authors:

,

,

Abstract

Vision-language models show inverse scaling on specific subtasks, where larger versions underperform smaller ones in areas like spatial reasoning and STEM questions, indicating that model choice should be task-specific.

Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance improvements. While this often holds at the aggregate level, we present systematic evidence that vision-language models (VLMs) exhibit inverse scaling at the subtask level: specific question categories on which larger models perform worse than smaller counterparts within the same model family. We evaluate 19 models from four distinct model families across eight multimodal benchmarks (nine evaluation splits), answering 29,386 questions per model, 558,334 model-question evaluations in total. Using per-question pairwise analysis across all model pairs in each family, we identify 375 subtask-model-pair combinations exhibiting inverse scaling, spanning 4,342 unique queries where a smaller model answers correctly but a larger model fails, and we find that these patterns replicate across independently developed architectures. We identify 13 subtask-dataset pairs that show inverse scaling across multiple families, consistent with the phenomenon being task-driven rather than model-specific. The most affected domains in our study include multi-image spatial reasoning, visual perception, and university-level STEM knowledge, with accuracy gaps exceeding 20 percentage points in several cases, while diagram understanding appears comparatively resistant. These findings challenge the assumption that increasing model size uniformly improves multimodal capabilities and suggest that model selection should be task-aware.

View arXiv page View PDF GitHub Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.27360 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.27360 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.27360 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co