From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Zefan, Qiu, Haoyi, Zhao, Haozhe, Wan, Ke, Li, Jiachen, Gu, Jiuxiang, Xiao, Wen, Peng, Nanyun, Hu, Junjie
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MMGR: Multi-Modal Generative Reasoning
by: Cai, Zefan, et al.
Published: (2025)

MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
by: Zhao, Haozhe, et al.
Published: (2025)

New Job, New Gender? Measuring the Social Bias in Image Generation Models
by: Wang, Wenxuan, et al.
Published: (2024)

Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies
by: Qiu, Haoyi, et al.
Published: (2025)

SafeWorld: Geo-Diverse Safety Alignment
by: Yin, Da, et al.
Published: (2024)

VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models
by: Qiu, Haoyi, et al.
Published: (2024)

METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling
by: Li, Bingxuan, et al.
Published: (2025)

AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation
by: Qiu, Haoyi, et al.
Published: (2023)

No Preference Left Behind: Group Distributional Preference Optimization
by: Yao, Binwei, et al.
Published: (2024)

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
by: Cai, Zefan, et al.
Published: (2025)

Evaluating Cultural and Social Awareness of LLM Web Agents
by: Qiu, Haoyi, et al.
Published: (2024)

Delta Attention Residuals
by: Luo, Cheng, et al.
Published: (2026)

Personalisation or Prejudice? Addressing Geographic Bias in Hate Speech Detection using Debias Tuning in Large Language Models
by: Piot, Paloma, et al.
Published: (2025)

Assessing GPT's Bias Towards Stigmatized Social Groups: An Intersectional Case Study on Nationality Prejudice and Psychophobia
by: Kashif, Afifah, et al.
Published: (2025)

Research as Resistance: Recognizing and Reconsidering HCI's Role in Technology Hype Cycles
by: Sramek, Zefan, et al.
Published: (2025)

Prompt and Prejudice
by: Berlincioni, Lorenzo, et al.
Published: (2024)

Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
by: Xu, Wenda, et al.
Published: (2024)

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
by: Liu, Runtao, et al.
Published: (2024)

Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
by: Zhu, Jingyuan, et al.
Published: (2026)

Evaluating Human Alignment and Model Faithfulness of LLM Rationale
by: Fayyaz, Mohsen, et al.
Published: (2024)

Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance
by: Jiang, Zhou, et al.
Published: (2026)

MMPersuade: A Dataset and Evaluation Framework for Multimodal Persuasion
by: Qiu, Haoyi, et al.
Published: (2025)

Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization
by: Pan, Yurui, et al.
Published: (2026)

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
by: Li, Ming, et al.
Published: (2024)

Discriminator-Free Direct Preference Optimization for Video Diffusion
by: Cheng, Haoran, et al.
Published: (2025)

Course-Correction: Safety Alignment Using Synthetic Preferences
by: Xu, Rongwu, et al.
Published: (2024)

LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
by: Zhang, Yanzhe, et al.
Published: (2023)

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
by: Gao, Songyang, et al.
Published: (2024)

Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models
by: Hwang, Sungwon, et al.
Published: (2025)

Self-Supervised Visual Preference Alignment
by: Zhu, Ke, et al.
Published: (2024)

Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning
by: Si, Shuzheng, et al.
Published: (2023)

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation
by: Zhao, Haozhe, et al.
Published: (2024)

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs
by: Wang, Xiaodong, et al.
Published: (2025)

Model Extrapolation Expedites Alignment
by: Zheng, Chujie, et al.
Published: (2024)

BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling
by: Yang, Jiachen, et al.
Published: (2026)

SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
by: Ye, Xi, et al.
Published: (2026)

RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment
by: Yang, Kevin, et al.
Published: (2023)

Improving Event Definition Following For Zero-Shot Event Detection
by: Cai, Zefan, et al.
Published: (2024)

Positional Bias in Binary Question Answering: How Uncertainty Shapes Model Preferences
by: Labruna, Tiziano, et al.
Published: (2025)

Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving
by: Wang, Zehao, et al.
Published: (2026)