Imagen de Portada

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Ao, Wang, Xiaoyu, Tan, Zhe, Li, Yu, Zhu, Jiachen, Su, Shu, Jia, Yuheng
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking
por: Zhu, Yabin, et al.
Publicado: (2026)

MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning
por: Zhang, Qizhe, et al.
Publicado: (2023)

DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval
por: Liu, Yating, et al.
Publicado: (2025)

Task-Customized Mixture of Adapters for General Image Fusion
por: Zhu, Pengfei, et al.
Publicado: (2024)

MoKA: Mixture of Kronecker Adapters
por: Sadeghi, Mohammadreza, et al.
Publicado: (2025)

LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
por: Qu, Xiaoye, et al.
Publicado: (2024)

Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters
por: Bhardwaj, Kartikeya, et al.
Publicado: (2024)

$D^2Prune$: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness
por: Xiong, Lang, et al.
Publicado: (2026)

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
por: Song, Kunpeng, et al.
Publicado: (2024)

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
por: Zhang, Yuheng, et al.
Publicado: (2024)

The Impact of International Students on UK Trade of Cultural Goods
por: Yuheng Lin, et al.
Publicado: (2025)

Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics
por: Wang, Jiashuo, et al.
Publicado: (2026)

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
por: Zhu, Tong, et al.
Publicado: (2024)

Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs
por: Williams, Tristan, et al.
Publicado: (2026)

Cross-Cultural Value Awareness in Large Vision-Language Models
por: Howard, Phillip, et al.
Publicado: (2026)

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
por: Yu, Jiazuo, et al.
Publicado: (2024)

Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection
por: Jin, Pengfei, et al.
Publicado: (2024)

Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation
por: Hu, Xiaoxing, et al.
Publicado: (2025)

MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts
por: Liao, Yusheng, et al.
Publicado: (2024)

DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
por: Zhu, Pengyun, et al.
Publicado: (2026)

Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
por: Jiang, Yukun, et al.
Publicado: (2026)

Sparse High Rank Adapters
por: Bhardwaj, Kartikeya, et al.
Publicado: (2024)

MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization
por: Zhang, Zhexin, et al.
Publicado: (2026)

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
por: Lin, Hongzhan, et al.
Publicado: (2024)

I Am Aligned, But With Whom? MENA Values Benchmark for Evaluating Cultural Alignment and Multilingual Bias in LLMs
por: Zahraei, Pardis Sadat, et al.
Publicado: (2025)

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
por: Li, Jiachen, et al.
Publicado: (2024)

Cultural Value Differences of LLMs: Prompt, Language, and Model Size
por: Zhong, Qishuai, et al.
Publicado: (2024)

Can GNN be Good Adapter for LLMs?
por: Huang, Xuanwen, et al.
Publicado: (2024)

Better Locally Private Sparse Estimation Given Multiple Samples Per User
por: Ma, Yuheng, et al.
Publicado: (2024)

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
por: Su, Yi, et al.
Publicado: (2025)

Align then Train: Efficient Retrieval Adapter Learning
por: Maekawa, Seiji, et al.
Publicado: (2026)

The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
por: Sun, Shangwen, et al.
Publicado: (2026)

Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization
por: Wang, Xingqi, et al.
Publicado: (2024)

Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
por: Arnob, Samin Yeasar, et al.
Publicado: (2025)

Random Initialization of Gated Sparse Adapters
por: Retault, Vi, et al.
Publicado: (2025)

Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting
por: Xu, Bowen, et al.
Publicado: (2024)

LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
por: Zhang, Renrui, et al.
Publicado: (2023)

SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
por: Mozaffari, Mohammad, et al.
Publicado: (2024)

Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
por: Petrova, Nora, et al.
Publicado: (2026)

MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter
por: Hao, Jitai, et al.
Publicado: (2024)