paper-with-me

홈 › Papers

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

2026-07-01 · Tien-Huy Nguyen, Minh-Nhat Nguyen, Nguyen Nhat Huy, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Thanh-Huy Nguyen, Cuong Tuan Nguyen, Hoang M. Le, Dat Nguyen, Phat Kim Huynh, Min Xu, Ulas Bagci arxiv

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/}.

📄 PDF Abstract BibTeX arXiv:2607.02089

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Reasoning

Similar Papers 제목 키워드 기반

RIV: Recursive Introspection Mask Diffusion Vision Language Model

2025-09-28 · YuQian Li, Limeng Qiao, Lin Ma arxiv

Mask Diffusion-based Vision Language Models (MDVLMs) have achieved remarkable progress in multimodal understanding tasks. However, these models are unable to correct errors in generated tokens, meaning they lack self-cor…

Learning Self-Correction in Vision-Language Models via Rollout Augmentation

2026-02-09 · Yi Ding, Ziliang Qiu, Bolian Li, Ruqi Zhang arxiv

Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning (RL) methods struggle to learn it, as effective self-correction behaviors eme…

Reinforcement Learning

PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policies

2026-06-25 · Jiayu Yang, Tao Yang, Weijun Li, Xiang Chang 외 arxiv

Long-horizon robotic manipulation is highly sensitive to physically infeasible transitions, contact-induced disturbances, and the lack of effective self-correction during execution. Although Vision-Language-Action (VLA) …

When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs

2024-06-03 · Ryo Kamoi, Yusen Zhang, Nan Zhang, Jiawei Han 외

Self-correction is an approach to improving responses from large language models (LLMs) by refining the responses using LLMs during inference. Prior work has proposed various self-correction frameworks using different so…

Survey

Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models

2024-02-19 · Loka Li, Zhenhao Chen, Guangyi Chen, Yixuan Zhang 외

The recent success of Large Language Models (LLMs) has catalyzed an increasing interest in their self-correction capabilities. This paper presents a comprehensive investigation into the intrinsic self-correction of LLMs,…