English
Related papers

Related papers: Steer Like the LLM: Activation Steering that Mimic…

200 papers

Large Language Models (LLMs) exhibit impressive performance across various domains but still struggle with arithmetic reasoning tasks. Recent work shows the effectiveness of prompt design methods in enhancing reasoning capabilities.…

Computation and Language · Computer Science 2024-10-11 Wenting Tan , Dongxiao Chen , Jieting Xue , Zihao Wang , Taijie Chen

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic…

Artificial Intelligence · Computer Science 2026-03-24 Johnathan Sun , Andrew Zhang

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-26 Kai-Wei Chang , Haibin Wu , Yu-Kai Wang , Yuan-Kuei Wu , Hua Shen , Wei-Cheng Tseng , Iu-thing Kang , Shang-Wen Li , Hung-yi Lee

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

Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…

Cryptography and Security · Computer Science 2025-11-24 Zhiyuan Xu , Stanislav Abaimov , Joseph Gardiner , Sana Belguith

Large Language Models (LLMs) exhibit remarkable proficiency in addressing a diverse array of tasks within the Natural Language Processing (NLP) domain, with various prompt design strategies significantly augmenting their capabilities.…

Computation and Language · Computer Science 2024-08-05 Xiangyu Zhao , Chengqian Ma

While test-time reasoning enables language models (LMs) to tackle complex tasks, searching or planning in natural language can be slow, costly, and error-prone. But even when LMs struggle to emulate the precise reasoning steps needed to…

Computation and Language · Computer Science 2025-08-11 Gabriel Grand , Joshua B. Tenenbaum , Vikash K. Mansinghka , Alexander K. Lew , Jacob Andreas

Large Language Models (LLMs) have shown impressive capabilities in many scenarios, but their performance depends, in part, on the choice of prompt. Past research has focused on optimizing prompts specific to a task. However, much less…

Computation and Language · Computer Science 2026-04-07 Lechen Zhang , Tolga Ergen , Lajanugen Logeswaran , Moontae Lee , David Jurgens

Current large language models have dangerous capabilities, which are likely to become more problematic in the future. Activation steering techniques can be used to reduce risks from these capabilities. In this paper, we investigate the…

Machine Learning · Computer Science 2024-03-12 Teun van der Weij , Massimo Poesio , Nandi Schoots

Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically…

Computation and Language · Computer Science 2025-09-30 Lucio La Cava , Andrea Tagarelli

Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLMs) without retraining or adaptation efforts. However,…

Computation and Language · Computer Science 2024-06-12 Jifeng Song , Kai Huang , Xiangyu Yin , Boyuan Yang , Wei Gao

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

Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time. However, current methods suffer from two key limitations:…

Artificial Intelligence · Computer Science 2026-02-24 Hongjue Zhao , Haosen Sun , Jiangtao Kong , Xiaochang Li , Qineng Wang , Liwei Jiang , Qi Zhu , Tarek Abdelzaher , Yejin Choi , Manling Li , Huajie Shao

Prompting language models (LMs) is the main interface for applying them to new tasks. However, for smaller LMs, prompting provides low accuracy compared to gradient-based finetuning. Tree Prompting is an approach to prompting which builds a…

Computation and Language · Computer Science 2023-10-24 John X. Morris , Chandan Singh , Alexander M. Rush , Jianfeng Gao , Yuntian Deng

Large language models (LLMs) have shown remarkable performance on many different Natural Language Processing (NLP) tasks. Prompt engineering plays a key role in adding more to the already existing abilities of LLMs to achieve significant…

Computation and Language · Computer Science 2024-07-25 Shubham Vatsal , Harsh Dubey

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

Computation and Language · Computer Science 2025-05-27 Ziang Zhou , Tianyuan Jin , Jieming Shi , Qing Li

Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training. We examine the seemingly obvious question: how to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Niccolo Avogaro , Thomas Frick , Mattia Rigotti , Andrea Bartezzaghi , Filip Janicki , Cristiano Malossi , Konrad Schindler , Roy Assaf

Recently, large language models (LLMs) have been successfully applied to many fields, showing outstanding comprehension and reasoning capabilities. Despite their great potential, LLMs usually require dedicated pre-training and fine-tuning…

Networking and Internet Architecture · Computer Science 2024-12-31 Hao Zhou , Chengming Hu , Dun Yuan , Ye Yuan , Di Wu , Xi Chen , Hina Tabassum , Xue Liu

LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings…

Large language models (LLMs) exhibit impressive capabilities in generation tasks but are prone to producing harmful, misleading, or biased content, posing significant ethical and safety concerns. To mitigate such risks, representation…

Cryptography and Security · Computer Science 2025-11-17 Zeqing He , Zhibo Wang , Huiyu Xu , Hejun Lin , Wenhui Zhang , Zhixuan Chu