Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?

ACL ARR 2025 May Submission2214 Authors

Abstract:

Recent advances in large language models (LLMs) have demonstrated that inference-time computation techniques, such as decoding-time scaling and self-refinement, can significantly enhance reasoning capabilities without relying on external knowledge. A key driver of this success is the emergence of self-correction and self-verification behaviors, often elicited through reinforcement learning (RL).

In this paper, we investigate whether these inference-time techniques extend effectively to vision-language models (VLMs), particularly those trained with RL. We find that while decoding strategies such as majority voting and best-of-N selection with self-verification all improve VLM reasoning performance, generation-reliant methods such as the former achieve significantly higher gains versus verification-reliant methods such as the latter. Additionally, the self-correction behavior often associated with RL-tuned models, such as “aha moment,” does not lead to measurable gains. We show via extensive experimentation within the inference-time scaling framework to identify a key root cause: RL-trained VLMs still lack robust self-verification capabilities across both visual and textual modalities.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: Visual Question Answering, Multimodality

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 2214