English
Related papers

Related papers: Steering Language Models with Weight Arithmetic

200 papers

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

In the training of large deep neural networks, there is a need for vast amounts of training data. To meet this need, data is collected from multiple domains, such as Wikipedia and GitHub. These domains are heterogeneous in both data quality…

Machine Learning · Computer Science 2025-11-11 Mahdi Salmani , Pratik Worah , Meisam Razaviyayn , Vahab Mirrokni

The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream and trained with a reinforcement-learning objective. These…

Model editing aims at selectively updating a small subset of a neural model's parameters with an interpretable strategy to achieve desired modifications. It can significantly reduce computational costs to adapt to large language models…

Computation and Language · Computer Science 2025-03-20 Shichen Li , Zhongqing Wang , Zheyu Zhao , Yue Zhang , Peifeng Li

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by…

Machine Learning · Computer Science 2024-06-21 Amrith Setlur , Saurabh Garg , Xinyang Geng , Naman Garg , Virginia Smith , Aviral Kumar

Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for robotics require finetuning to contend with varying…

Weight-perturbation evolution strategies (ES) can fine-tune billion-parameter language models with surprisingly small populations (e.g., $N\!\approx\!30$), contradicting classical zeroth-order curse-of-dimensionality intuition. We also…

Machine Learning · Computer Science 2026-02-03 Qiyao Liang , Jinyeop Song , Yizhou Liu , Jeff Gore , Ila Fiete , Risto Miikkulainen , Xin Qiu

Large language models (LLMs) operate as autoregressive predictors over discrete token vocabularies, a formulation that has enabled their adaptation far beyond natural language to vision, robotics, and multimodal reasoning. However, training…

Machine Learning · Computer Science 2026-05-08 Jiwan Chung , Saejin Kim , Yongrae Jo , Jaewoo Park , Dongjun Min , Youngjae Yu

Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are quantized with the objective of minimizing quantization…

Machine Learning · Computer Science 2024-11-07 Khasmamad Shabanovi , Lukas Wiest , Vladimir Golkov , Daniel Cremers , Thomas Pfeil

Multimodal large language models (MLLMs) have demonstrated extraordinary capabilities in conducting conversations based on image inputs. However, we observe that MLLMs exhibit a pronounced form of visual sycophantic behavior. While similar…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Renjie Pi , Kehao Miao , Li Peihang , Runtao Liu , Jiahui Gao , Jipeng Zhang , Xiaofang Zhou

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Computation and Language · Computer Science 2024-09-10 Sonam Gupta , Yatin Nandwani , Asaf Yehudai , Mayank Mishra , Gaurav Pandey , Dinesh Raghu , Sachindra Joshi

The alignment process changes several properties of a large language model's (LLM's) output distribution. We analyze two aspects of post-alignment distributional shift of LLM responses. First, we re-examine previously reported reductions in…

Computation and Language · Computer Science 2025-05-13 Thom Lake , Eunsol Choi , Greg Durrett

While various avenues of research have been explored for iterative pruning, little is known what effect pruning has on zero-shot test performance and its potential implications on the choice of pruning criteria. This pruning setup is…

Computation and Language · Computer Science 2022-04-06 James O' Neill , Sourav Dutta , Haytham Assem

Reinforcement Learning from Human Feedback (RLHF), using algorithms like Proximal Policy Optimization (PPO), aligns Large Language Models (LLMs) with human values but is costly and unstable. Alternatives have been proposed to replace PPO or…

Computation and Language · Computer Science 2026-04-03 Liang Zhu , Feiteng Fang , Yuelin Bai , Longze Chen , Zhexiang Zhang , Minghuan Tan , Min Yang

In the covariate shift learning scenario, the training and test covariate distributions differ, so that a predictor's average loss over the training and test distributions also differ. In this work, we explore the potential of extreme…

Machine Learning · Computer Science 2018-03-13 Fulton Wang , Cynthia Rudin

Contrastive steering has been shown as a simple and effective method to adjust the generative behavior of LLMs at inference time. It uses examples of prompt responses with and without a trait to identify a direction in an intermediate…

Machine Learning · Computer Science 2026-03-04 Cullen Anderson , Narmeen Oozeer , Foad Namjoo , Remy Ogasawara , Amirali Abdullah , Jeff M. Phillips

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…

Computation and Language · Computer Science 2024-06-07 Chi Han , Jialiang Xu , Manling Li , Yi Fung , Chenkai Sun , Nan Jiang , Tarek Abdelzaher , Heng Ji

We study linear regression under covariate shift, where the marginal distribution over the input covariates differs in the source and the target domains, while the conditional distribution of the output given the input covariates is similar…

Machine Learning · Computer Science 2022-08-04 Jingfeng Wu , Difan Zou , Vladimir Braverman , Quanquan Gu , Sham M. Kakade

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

Fine-tuning large language models (LLMs) can lead to unintended out-of-distribution generalization. Standard approaches to this problem rely on modifying training data, for example by adding data that better specify the intended…

Machine Learning · Computer Science 2025-11-11 Helena Casademunt , Caden Juang , Adam Karvonen , Samuel Marks , Senthooran Rajamanoharan , Neel Nanda
‹ Prev 1 4 5 6 7 8 10 Next ›