English
Related papers

Related papers: Extending Activation Steering to Broad Skills and …

200 papers

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…

Machine Learning · Computer Science 2026-04-07 Soham Gadgil , Chris Lin , Su-In Lee

Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another. Depending on the input, they may over-rely on linguistic priors relative to visual evidence, or…

Machine Learning · Computer Science 2026-02-16 Zihan Huang , Xintong Li , Rohan Surana , Tong Yu , Rui Wang , Julian McAuley , Jingbo Shang , Junda Wu

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning…

Computation and Language · Computer Science 2025-07-17 Yanjian Zhang , Guillaume Wisniewski , Nadi Tomeh , Thierry Charnois

Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and redundant reasoning steps that increase computational costs while potentially degrading…

Computation and Language · Computer Science 2026-04-14 Aryasomayajula Ram Bharadwaj

Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…

Large language models (LLMs) are increasingly used as autonomous agents in strategic and social interactions. Although recent studies suggest that assigning personality traits to LLMs can influence their behavior, how personality steering…

Artificial Intelligence · Computer Science 2026-01-15 Mizuki Sakai , Mizuki Yokoyama , Wakaba Tateishi , Genki Ichinose

Large Language Models have many methods for solving the same problem. This introduces novel strengths (different methods may work well for different problems) and weaknesses (it may be difficult for users to know which method to use). In…

Computation and Language · Computer Science 2023-07-21 Shriyash K. Upadhyay , Etan J. Ginsberg

Classic results establish that encouraging predictive diversity improves performance in ensembles of low-capacity models, e.g. through bagging or boosting. Here we demonstrate that these intuitions do not apply to high-capacity neural…

Machine Learning · Computer Science 2024-01-11 Taiga Abe , E. Kelly Buchanan , Geoff Pleiss , John P. Cunningham

Generative artificial intelligence models learn probability distributions from data and produce novel samples that capture the salient properties of their training sets. Proteins are particularly attractive for such approaches given their…

Biomolecules · Quantitative Biology 2026-02-27 Filippo Stocco , Michele Garibbo , Noelia Ferruz

Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should…

Machine Learning · Computer Science 2020-02-19 Matthew C. Robinson , Robert C. Glen , Alpha A. Lee

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Computation and Language · Computer Science 2026-03-17 Amr Hegazy , Mostafa Elhoushi , Amr Alanwar

Activation steering controls LLM behaviour towards target behaviour by intervening in internal representations, yet it often degrades reasoning and retrieval performance. We argue that a primary cause of this trade-off is attention…

Computation and Language · Computer Science 2026-05-08 Haoyan Luo , Mateo Espinosa Zarlenga , Mateja Jamnik

Mechanistic interpretability seeks to understand the internal mechanisms of machine learning models, where localization -- identifying the important model components -- is a key step. Activation patching, also known as causal tracing or…

Machine Learning · Computer Science 2024-01-18 Fred Zhang , Neel Nanda

Achieving high-performing language models which include medium- and lower-resource languages remains a challenge. Massively multilingual models still underperform compared to language-specific adaptations, especially at smaller model…

Computation and Language · Computer Science 2025-12-12 Kevin Glocker , Kätriin Kukk , Romina Oji , Marcel Bollmann , Marco Kuhlmann , Jenny Kunz

Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradigm also introduces new safety challenges. Since only a subset…

Cryptography and Security · Computer Science 2026-05-01 Jona te Lintelo , Lichao Wu , Marina Krček , Sengim Karayalçin , Stjepan Picek

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

Computation and Language · Computer Science 2023-11-29 Utsav Garg , Erhan Bas

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

Machine Learning · Computer Science 2025-10-07 Zhepeng Cen , Yihang Yao , William Han , Zuxin Liu , Ding Zhao

The objective of this work is to augment the basic abilities of a robot by learning to use new sensorimotor primitives to enable the solution of complex long-horizon problems. Solving long-horizon problems in complex domains requires…

Robotics · Computer Science 2018-08-14 Zi Wang , Caelan Reed Garrett , Leslie Pack Kaelbling , Tomás Lozano-Pérez

We examine two properties of AI systems: capability (what a system can do) and steerability (how reliably one can shift behavior toward intended outcomes). A central question is whether capability growth reduces steerability and risks…

Computation and Language · Computer Science 2026-01-07 Jakub Hoscilowicz

We investigated motor skill learning using a path tracking task, where human subjects had to track various curved paths as fast as possible, in the absence of any external perturbations. Subjects became better with practice, producing…

Neurons and Cognition · Quantitative Biology 2024-06-06 Luke Bashford , Dmitry Kobak , Carsten Mehring