English
Related papers

Related papers: Steering MoE LLMs via Expert (De)Activation

200 papers

Sparse Mixture-of-Experts (MoE) architectures are increasingly popular for frontier large language models (LLM) but they introduce training challenges due to routing complexity. Fully leveraging parameters of an MoE model requires all…

Next location prediction plays a critical role in understanding human mobility patterns. However, existing approaches face two core limitations: (1) they fall short in capturing the complex, multi-functional semantics of real-world…

Artificial Intelligence · Computer Science 2025-06-02 Shuai Liu , Ning Cao , Yile Chen , Yue Jiang , Gao Cong

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Cryptography and Security · Computer Science 2026-02-06 Chen Xiong , Zhiyuan He , Pin-Yu Chen , Ching-Yun Ko , Tsung-Yi Ho

Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs)…

Computation and Language · Computer Science 2026-05-12 Ryan Wang , Akshita Bhagia , Sewon Min

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. When comparing MoE to dense models, prior work typically adopt the following setting: 1) use FLOPs or activated…

Machine Learning · Computer Science 2024-07-02 Xianzhi Du , Tom Gunter , Xiang Kong , Mark Lee , Zirui Wang , Aonan Zhang , Nan Du , Ruoming Pang

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Machine Learning · Computer Science 2026-04-20 Zixuan Weng , Jinghuai Zhang , Kunlin Cai , Ying Li , Peiran Wang , Yuan Tian

Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains…

Computation and Language · Computer Science 2026-02-11 Nam V. Nguyen , Thong T. Doan , Luong Tran , Van Nguyen , Quang Pham

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Computation and Language · Computer Science 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Computation and Language · Computer Science 2025-06-04 Mengru Wang , Ziwen Xu , Shengyu Mao , Shumin Deng , Zhaopeng Tu , Huajun Chen , Ningyu Zhang

While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using…

Machine Learning · Computer Science 2026-05-15 Bat-Sheva Einbinder , Hen Davidov , Yee Whye Teh , Yarin Gal , Yaniv Romano

The Mixture of Experts (MoE) architecture enables the scaling of Large Language Models (LLMs) to trillions of parameters by activating a sparse subset of weights for each input, maintaining constant computational cost during inference.…

Machine Learning · Computer Science 2026-01-08 Shihao Ji , Zihui Song

Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting remain underexplored. In this work, we study multilingual routing dynamics during continual…

Computation and Language · Computer Science 2026-05-29 Aditi Khandelwal , Marius Mosbach , Verna Dankers , Siva Reddy , Golnoosh Farnadi

Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such…

Machine Learning · Computer Science 2025-11-04 Jayneel Parekh , Pegah Khayatan , Mustafa Shukor , Arnaud Dapogny , Alasdair Newson , Matthieu Cord

Scaling the size of a model enhances its capabilities but significantly increases computation complexity. Mixture-of-Experts models (MoE) address the issue by allowing model size to scale up without substantially increasing training or…

Computation and Language · Computer Science 2024-08-30 Zhenpeng Su , Zijia Lin , Xue Bai , Xing Wu , Yizhe Xiong , Haoran Lian , Guangyuan Ma , Hui Chen , Guiguang Ding , Wei Zhou , Songlin Hu

The sparse Mixture-of-Experts (MoE) architecture of large language models (LLMs) confronts an inherent issue of load imbalance arising from the simplistic linear router strategy, which ultimately causes the instability and inefficient…

Machine Learning · Computer Science 2025-11-25 Ting Bai , Yue Yu , Le Huang , Zenan Xu , Chuan Shi

In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input…

Machine Learning · Computer Science 2024-03-13 Quzhe Huang , Zhenwei An , Nan Zhuang , Mingxu Tao , Chen Zhang , Yang Jin , Kun Xu , Kun Xu , Liwei Chen , Songfang Huang , Yansong Feng

Sparse Mixture of Experts (SMoE) enables efficient training of large language models by routing input tokens to a select number of experts. However, training SMoE remains challenging due to the issue of representation collapse. Recent…

Computation and Language · Computer Science 2025-04-01 Giang Do , Hung Le , Truyen Tran

Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduces a new attack surface: the routing mechanism that…

Cryptography and Security · Computer Science 2026-05-07 Zekun Fei , Zihao Wang , Weijie Liu , Ruiqi He , Jianing Geng , Zheli Liu , XiaoFeng Wang

By introducing routers to selectively activate experts in Transformer layers, the mixture-of-experts (MoE) architecture significantly reduces computational costs in large language models (LLMs) while maintaining competitive performance,…

Machine Learning · Computer Science 2026-02-10 Yukun Jiang , Hai Huang , Mingjie Li , Yage Zhang , Michael Backes , Yang Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›