ESC: Emotional Self-Correction for Reliable Vision-Language Models

2026-07-01

AI Summary

This work addresses the unreliability of existing vision-language models in multimodal reasoning, a limitation exacerbated by current self-correction approaches that rely on additional training or complex feedback mechanisms with high computational overhead. To overcome this, the paper proposes ESC—an entirely training-free self-correction framework that introduces emotional signals as a novel triggering mechanism. ESC employs an external validator to detect erroneous responses and injects affective feedback to prompt the model to autonomously reflect on and revise its outputs. Without modifying the model architecture or requiring any extra training, ESC significantly enhances model reliability across multiple benchmarks, including safety, hallucination suppression, visual perception, and multimodal reasoning, while preserving overall performance.

Abstract

Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Existing self-correction methods mitigate these issues but typically rely on post-training or carefully engineered feedback, incurring high computational cost. In this work, we revisit this challenge through the lens of emotional cues, asking whether they can activate latent self-correction behaviors in VLMs without additional training. \textbf{We find that emotional signals serve as an effective trigger for self-correction, encouraging more cautious and reflective reasoning}. Motivated by this finding, we propose \escabstract (\textbf{\underline{E}}motional \textbf{\underline{S}}elf-\textbf{\underline{C}}orrection), a training-free self-correction framework. ESC introduces an external verifier that detects potentially incorrect initial responses and injects emotional feedback to encourage model to reflect, and produce a better revised response without additional training. Extensive experiments across safety, hallucination, vision-centric perception, and multimodal reasoning benchmarks show that ESC consistently improves reliability while preserving overall model utility. These results suggest that emotion can function not only as an ability to be recognized, but also as a practical control signal for scalable self-correction in VLMs. \textbf{We therefore believe that ESC provides a strong foundation for a new reliable human-like, emotion-integrated research direction.} Our project is publicly available at \textcolor{red}{https://genai4e.github.io/ESC/}.

Problem

• Vision-Language Models
• Self-Correction
• Reliability
• Emotional Cues
• Hallucination

Innovation

• Emotional Self-Correction
• Vision-Language Models
• Training-Free
• Reliability
• Multimodal Reasoning