Imagen de Portada

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Xiaoqing, Chen, Ruizhe, Zan, Hongying, Jia, Yuxiang, Peng, Min
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Detection, Classification, and Mitigation of Gender Bias in Large Language Models
por: Cheng, Xiaoqing, et al.
Publicado: (2025)

BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models
por: Fan, Zhiting, et al.
Publicado: (2025)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
por: Li, Yichen, et al.
Publicado: (2025)

MRC-based Nested Medical NER with Co-prediction and Adaptive Pre-training
por: Du, Xiaojing, et al.
Publicado: (2024)

Race, Ethnicity and Their Implication on Bias in Large Language Models
por: Hu, Shiyue, et al.
Publicado: (2026)

A Corpus for Named Entity Recognition in Chinese Novels with Multi-genres
por: Zhao, Hanjie, et al.
Publicado: (2023)

ZZU-NLP at SIGHAN-2024 dimABSA Task: Aspect-Based Sentiment Analysis with Coarse-to-Fine In-context Learning
por: Zhu, Senbin, et al.
Publicado: (2024)

Large Language Model Bias Mitigation from the Perspective of Knowledge Editing
por: Chen, Ruizhe, et al.
Publicado: (2024)

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

BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
por: Xu, Xin, et al.
Publicado: (2025)

DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models
por: Chen, Ruizhe, et al.
Publicado: (2025)

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

SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis
por: Zhu, Senbin, et al.
Publicado: (2024)

Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation
por: Zhu, Qin, et al.
Publicado: (2024)

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

Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Models
por: Apsel, Molly, et al.
Publicado: (2026)

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

Gender Bias in Large Language Models across Multiple Languages
por: Zhao, Jinman, et al.
Publicado: (2024)

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

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

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

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

Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making
por: Lyu, Yougang, et al.
Publicado: (2025)

Identifying and Mitigating Social Bias Knowledge in Language Models
por: Chen, Ruizhe, et al.
Publicado: (2024)

JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling
por: Song, Jinwang, et al.
Publicado: (2025)

BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs
por: Fan, Zhiting, et al.
Publicado: (2024)

Debiasing Reward Models via Causally Motivated Inference-Time Intervention
por: Shinoda, Kazutoshi, et al.
Publicado: (2026)

Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models
por: Kuzmin, Gleb, et al.
Publicado: (2024)

Filter-then-Generate: Large Language Models with Structure-Text Adapter for Knowledge Graph Completion
por: Liu, Ben, et al.
Publicado: (2024)

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

Self-Debias: Self-correcting for Debiasing Large Language Models
por: Feng, Xuan, et al.
Publicado: (2026)

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
por: Zhang, Tao, et al.
Publicado: (2024)

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

Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models
por: Rao, Pooja S. B., et al.
Publicado: (2025)

Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization
por: Wang, Yaoxiang, et al.
Publicado: (2025)

TimeBill: Time-Budgeted Inference for Large Language Models
por: Fan, Qi, et al.
Publicado: (2025)

Text Prompt Injection of Vision Language Models
por: Zhu, Ruizhe
Publicado: (2025)

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

Can the capability of Large Language Models be described by human ability? A Meta Study
por: Zan, Mingrui, et al.
Publicado: (2025)

Improving Natural Language Capability of Code Large Language Model
por: Li, Wei, et al.
Publicado: (2024)