Cover Image

Self-Consistency as a Free Lunch: Reducing Hallucinations in Vision-Language Models via Self-Reflection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Mingfei, Hao, Haihong, Zhou, Jinxing, Li, Zhihui, Zheng, Yuhui, Deng, Xueqing, Yang, Linjie, Chang, Xiaojun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
by: Hao, Haihong, et al.
Published: (2025)

LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning
by: Hao, Haihong, et al.
Published: (2026)

Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos
by: Han, Mingfei, et al.
Published: (2026)

Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
by: Han, Mingfei, et al.
Published: (2023)

Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions
by: Zhang, Kecheng, et al.
Published: (2026)

Vision-Language Models Can Self-Improve Reasoning via Reflection
by: Cheng, Kanzhi, et al.
Published: (2024)

Re-ReST: Reflection-Reinforced Self-Training for Language Agents
by: Dou, Zi-Yi, et al.
Published: (2024)

GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning
by: Liu, Ruiheng, et al.
Published: (2026)

Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation
by: Jin, Minghao, et al.
Published: (2026)

Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models
by: Jiang, Longtao, et al.
Published: (2025)

Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation
by: Zhou, Jinxing, et al.
Published: (2025)

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
by: Wang, Shan, et al.
Published: (2025)

Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation
by: Zhou, Jinxing, et al.
Published: (2025)

Online Self-Calibration Against Hallucination in Vision-Language Models
by: Chen, Minghui, et al.
Published: (2026)

See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation
by: Dai, Tingjun, et al.
Published: (2026)

LongVLM: Efficient Long Video Understanding via Large Language Models
by: Weng, Yuetian, et al.
Published: (2024)

Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration
by: Zhou, Ziheng, et al.
Published: (2024)

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
by: Wu, Changlong, et al.
Published: (2024)

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
by: Lu, Yifan, et al.
Published: (2025)

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
by: Liu, Zhiheng, et al.
Published: (2025)

Towards Self-Refinement of Vision-Language Models with Triangular Consistency
by: Deng, Yunlong, et al.
Published: (2025)

From Emergence to Control: Probing and Modulating Self-Reflection in Language Models
by: Zhu, Xudong, et al.
Published: (2025)

Learning A Zero-shot Occupancy Network from Vision Foundation Models via Self-supervised Adaptation
by: Lin, Sihao, et al.
Published: (2025)

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
by: Wang, Chenfeng, et al.
Published: (2026)

Language Models and Cycle Consistency for Self-Reflective Machine Translation
by: Wangni, Jianqiao
Published: (2024)

Skip \n: A Simple Method to Reduce Hallucination in Large Vision-Language Models
by: Han, Zongbo, et al.
Published: (2024)

Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
by: Zhang, Jinrui, et al.
Published: (2024)

Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
by: Jiang, Yibo, et al.
Published: (2026)

User-Feedback-Driven Adaptation for Vision-and-Language Navigation
by: Yu, Yongqiang, et al.
Published: (2025)

FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers
by: Zhang, Yanbing, et al.
Published: (2025)

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
by: Wang, Zehan, et al.
Published: (2024)

Reducing Hallucinations in Vision-Language Models via Latent Space Steering
by: Liu, Sheng, et al.
Published: (2024)

No Free Lunch with Guardrails
by: Kumar, Divyanshu, et al.
Published: (2025)

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
by: Wu, Tsung-Han, et al.
Published: (2025)

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
by: Huo, Fushuo, et al.
Published: (2024)

"Having Lunch Now": Understanding How Users Engage with a Proactive Agent for Daily Planning and Self-Reflection
by: Abbas, Adnan, et al.
Published: (2025)

Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection
by: Liu, MingShan, et al.
Published: (2025)

EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
by: Lin, Bingqian, et al.
Published: (2025)

SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding
by: Wu, Chang-Hsun, et al.
Published: (2025)

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs
by: Ge, Haonan, et al.
Published: (2025)