Cover Image

Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Dachuan, Li, Weiyue, Shen, Zhenda, Qiu, Yushu, Xu, Bowen, Chen, Haoyu, Chen, Yongchao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback
by: Li, Weiyue, et al.
Published: (2026)

Post-hoc Reward Calibration: A Case Study on Length Bias
by: Huang, Zeyu, et al.
Published: (2024)

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
by: Cheng, Xiaoqing, et al.
Published: (2025)

Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models
by: Hao, Teqi, et al.
Published: (2025)

Rethinking Prompt-based Debiasing in Large Language Models
by: Yang, Xinyi, et al.
Published: (2025)

Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
by: Zhou, Hongli, et al.
Published: (2026)

BiasEdit: Debiasing Stereotyped Language Models via Model Editing
by: Xu, Xin, et al.
Published: (2025)

On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection
by: Elsafoury, Fatma, et al.
Published: (2023)

VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models
by: Raj, Chahat, et al.
Published: (2025)

Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
by: Lin, Yujie, et al.
Published: (2026)

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
by: Dhaini, Mahdi, et al.
Published: (2025)

Bias Beyond English: Evaluating Social Bias and Debiasing Methods in a Low-Resource Setting
by: Zhou, Ej, et al.
Published: (2025)

Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
by: Peng, Guangyue, et al.
Published: (2026)

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification
by: Yang, Dingkang, et al.
Published: (2024)

Harnessing Large Language Models as Post-hoc Correctors
by: Zhong, Zhiqiang, et al.
Published: (2024)

Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
by: Yang, Haoyan, et al.
Published: (2025)

Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategies
by: Abrar, Ajwad, et al.
Published: (2025)

OffsetBias: Leveraging Debiased Data for Tuning Evaluators
by: Park, Junsoo, et al.
Published: (2024)

LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models
by: Liu, Tianci, et al.
Published: (2024)

Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models
by: Liang, Haoyu, et al.
Published: (2026)

From Measurement to Mitigation: Exploring the Transferability of Debiasing Approaches to Gender Bias in Maltese Language Models
by: Galea, Melanie, et al.
Published: (2025)

Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models
by: Lei, Xuanyu, et al.
Published: (2024)

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
by: Yeo, Wei Jie, et al.
Published: (2025)

Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective
by: Zhao, Yunxiao, et al.
Published: (2025)

EvoMerge: Neuroevolution for Large Language Models
by: Jiang, Yushu
Published: (2024)

FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge
by: Yang, Bo, et al.
Published: (2026)

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
by: Shi, Dachuan, et al.
Published: (2023)

Sounding Like a Winner? Prosodic Differences in Post-Match Interviews
by: Kakouros, Sofoklis, et al.
Published: (2025)

Rethinking Token Reduction for State Space Models
by: Zhan, Zheng, et al.
Published: (2024)

Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection
by: Spliethöver, Maximilian, et al.
Published: (2025)

The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing
by: Kaneko, Masahiro, et al.
Published: (2024)

Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data
by: Gorti, Atmika, et al.
Published: (2024)

Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
by: Wang, Xintong, et al.
Published: (2025)

debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
by: Sasse, Kuleen, et al.
Published: (2024)

Causal-Guided Active Learning for Debiasing Large Language Models
by: Du, Li, et al.
Published: (2024)

Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought
by: Li, Bowen, et al.
Published: (2026)

Coordinated Semantic Alignment and Evidence Constraints for Retrieval-Augmented Generation with Large Language Models
by: Chen, Xin, et al.
Published: (2026)

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
by: Zhou, Yucheng, et al.
Published: (2024)

Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
by: Liusie, Adian, et al.
Published: (2024)

Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
by: Liu, Guangliang, et al.
Published: (2024)