Imagen de Portada

An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shirafuji, Daiki, Saito, Tatsuhiko, Kimura, Yasutomo
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Hybrid Search for Complex Table Question Answering in Securities Report
por: Shirafuji, Daiki, et al.
Publicado: (2025)

Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
por: Shirafuji, Daiki, et al.
Publicado: (2024)

Bridging the Modality Gap by Similarity Standardization with Pseudo-Positive Samples
por: Yamashita, Shuhei, et al.
Publicado: (2025)

GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients
por: Kazama, Kentaro, et al.
Publicado: (2026)

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

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
por: Ma, Qianli, et al.
Publicado: (2025)

Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation
por: Luo, Guoqing, et al.
Publicado: (2025)

Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
por: Wu, Xuyang, et al.
Publicado: (2025)

The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging
por: Lan, Xiaochong, et al.
Publicado: (2025)

Refactoring Programs Using Large Language Models with Few-Shot Examples
por: Shirafuji, Atsushi, et al.
Publicado: (2023)

Locating and Mitigating Gender Bias in Large Language Models
por: Cai, Yuchen, et al.
Publicado: (2024)

Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging
por: Wang, Zhixiang, et al.
Publicado: (2025)

Likelihood-based Mitigation of Evaluation Bias in Large Language Models
por: Oi, Masanari, et al.
Publicado: (2024)

Multi-Persona Thinking for Bias Mitigation in Large Language Models
por: Chen, Yuxing, et al.
Publicado: (2026)

The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs
por: Kraft, Angelie, et al.
Publicado: (2022)

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

Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction
por: Saito, Kuniaki, et al.
Publicado: (2024)

SuperMerge: An Approach For Gradient-Based Model Merging
por: Yang, Haoyu, et al.
Publicado: (2024)

Mitigating Bias for Question Answering Models by Tracking Bias Influence
por: Ma, Mingyu Derek, et al.
Publicado: (2023)

Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations
por: Dimgba, Martha O., et al.
Publicado: (2025)

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

Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models
por: Parihar, Shweta, et al.
Publicado: (2026)

Understanding and Mitigating Tokenization Bias in Language Models
por: Phan, Buu, et al.
Publicado: (2024)

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
por: Zhou, Hanzhang, et al.
Publicado: (2024)

Transport and Merge: Cross-Architecture Merging for Large Language Models
por: Cui, Chenhang, et al.
Publicado: (2026)

Steering Towards Fairness: Mitigating Political Bias in LLMs
por: Nadeem, Afrozah, et al.
Publicado: (2025)

Mitigating Metric Bias in Minimum Bayes Risk Decoding
por: Kovacs, Geza, et al.
Publicado: (2024)

Implicit Bias in LLMs: A Survey
por: Lin, Xinru, et al.
Publicado: (2025)

LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models
por: Qin, Zhanyue, et al.
Publicado: (2025)

Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
por: Xu, Yue, et al.
Publicado: (2025)

Style Transfer as Bias Mitigation: Diffusion Models for Synthetic Mental Health Text for Arabic
por: Mankarious, Saad, et al.
Publicado: (2026)

Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models
por: Lu, Zhenyi, et al.
Publicado: (2024)

MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs
por: Zhou, Yuhang, et al.
Publicado: (2025)

SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging
por: Chen, Zijun, et al.
Publicado: (2025)

A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias
por: Xu, Yuemei, et al.
Publicado: (2024)

No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases
por: Chand, Shireen, et al.
Publicado: (2025)

Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
por: Liu, Shuqi, et al.
Publicado: (2025)

Mitigating Length Bias in RLHF through a Causal Lens
por: Kim, Hyeonji, et al.
Publicado: (2025)

A Variational Approach for Mitigating Entity Bias in Relation Extraction
por: Mensah, Samuel, et al.
Publicado: (2025)

Equilibrium Dynamics and Mitigation of Gender Bias in Synthetically Generated Data
por: Kattamuri, Ashish, et al.
Publicado: (2025)