Image de couverture de livre

An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shirafuji, Daiki, Saito, Tatsuhiko, Kimura, Yasutomo
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Hybrid Search for Complex Table Question Answering in Securities Report
par: Shirafuji, Daiki, et autres
Publié: (2025)

Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
par: Shirafuji, Daiki, et autres
Publié: (2024)

Bridging the Modality Gap by Similarity Standardization with Pseudo-Positive Samples
par: Yamashita, Shuhei, et autres
Publié: (2025)

GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients
par: Kazama, Kentaro, et autres
Publié: (2026)

Identifying and Mitigating Social Bias Knowledge in Language Models
par: Chen, Ruizhe, et autres
Publié: (2024)

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
par: Ma, Qianli, et autres
Publié: (2025)

Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation
par: Luo, Guoqing, et autres
Publié: (2025)

Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
par: Wu, Xuyang, et autres
Publié: (2025)

The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging
par: Lan, Xiaochong, et autres
Publié: (2025)

Refactoring Programs Using Large Language Models with Few-Shot Examples
par: Shirafuji, Atsushi, et autres
Publié: (2023)

Locating and Mitigating Gender Bias in Large Language Models
par: Cai, Yuchen, et autres
Publié: (2024)

Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging
par: Wang, Zhixiang, et autres
Publié: (2025)

Likelihood-based Mitigation of Evaluation Bias in Large Language Models
par: Oi, Masanari, et autres
Publié: (2024)

Multi-Persona Thinking for Bias Mitigation in Large Language Models
par: Chen, Yuxing, et autres
Publié: (2026)

The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs
par: Kraft, Angelie, et autres
Publié: (2022)

Large Language Model Bias Mitigation from the Perspective of Knowledge Editing
par: Chen, Ruizhe, et autres
Publié: (2024)

Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction
par: Saito, Kuniaki, et autres
Publié: (2024)

SuperMerge: An Approach For Gradient-Based Model Merging
par: Yang, Haoyu, et autres
Publié: (2024)

Mitigating Bias for Question Answering Models by Tracking Bias Influence
par: Ma, Mingyu Derek, et autres
Publié: (2023)

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

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
par: Zhang, Tao, et autres
Publié: (2024)

Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models
par: Parihar, Shweta, et autres
Publié: (2026)

Understanding and Mitigating Tokenization Bias in Language Models
par: Phan, Buu, et autres
Publié: (2024)

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
par: Zhou, Hanzhang, et autres
Publié: (2024)

Transport and Merge: Cross-Architecture Merging for Large Language Models
par: Cui, Chenhang, et autres
Publié: (2026)

Steering Towards Fairness: Mitigating Political Bias in LLMs
par: Nadeem, Afrozah, et autres
Publié: (2025)

Mitigating Metric Bias in Minimum Bayes Risk Decoding
par: Kovacs, Geza, et autres
Publié: (2024)

Implicit Bias in LLMs: A Survey
par: Lin, Xinru, et autres
Publié: (2025)

LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models
par: Qin, Zhanyue, et autres
Publié: (2025)

Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
par: Xu, Yue, et autres
Publié: (2025)

Style Transfer as Bias Mitigation: Diffusion Models for Synthetic Mental Health Text for Arabic
par: Mankarious, Saad, et autres
Publié: (2026)

Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models
par: Lu, Zhenyi, et autres
Publié: (2024)

MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs
par: Zhou, Yuhang, et autres
Publié: (2025)

SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging
par: Chen, Zijun, et autres
Publié: (2025)

A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias
par: Xu, Yuemei, et autres
Publié: (2024)

No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases
par: Chand, Shireen, et autres
Publié: (2025)

Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
par: Liu, Shuqi, et autres
Publié: (2025)

Mitigating Length Bias in RLHF through a Causal Lens
par: Kim, Hyeonji, et autres
Publié: (2025)

A Variational Approach for Mitigating Entity Bias in Relation Extraction
par: Mensah, Samuel, et autres
Publié: (2025)

Equilibrium Dynamics and Mitigation of Gender Bias in Synthetically Generated Data
par: Kattamuri, Ashish, et autres
Publié: (2025)