English
Related papers

Related papers: Improving Activation Steering in Language Models w…

200 papers

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…

Computation and Language · Computer Science 2025-10-02 Zifeng Cheng , Jinwei Gan , Zhiwei Jiang , Cong Wang , Yafeng Yin , Xiang Luo , Yuchen Fu , Qing Gu

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even…

Computation and Language · Computer Science 2024-10-03 Amrita Bhattacharjee , Shaona Ghosh , Traian Rebedea , Christopher Parisien

We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying their activations during forward passes. CAA computes "steering vectors" by averaging the difference in residual stream…

Computation and Language · Computer Science 2024-07-08 Nina Panickssery , Nick Gabrieli , Julian Schulz , Meg Tong , Evan Hubinger , Alexander Matt Turner

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the…

Computation and Language · Computer Science 2025-02-26 Weixuan Wang , Jingyuan Yang , Wei Peng

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…

Computation and Language · Computer Science 2026-02-03 Jiaqian Li , Yanshu Li , Kuan-Hao Huang

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

Accent variability remains a major errors in automatic speech recognition, yet most adaptation methods rely on parameter fine-tuning without understanding where accent information is encoded. We treat accent variation as an interpretable…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-09 Jinuo Sun , Yang Xiao , Sung Kyun Chung , Qiuchi Hu , Gongping Huang , Eun-Jung Holden , Ting Dang

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually…

Machine Learning · Computer Science 2025-10-16 Anna Hedström , Salim I. Amoukou , Tom Bewley , Saumitra Mishra , Manuela Veloso

Best-of-$N$ reasoning improves the accuracy of language models in solving complex tasks by sampling multiple candidate solutions and then selecting the best one based on some criteria. A critical bottleneck for this strategy is the output…

Machine Learning · Computer Science 2025-11-12 Ly Tran Ho Khanh , Dongxuan Zhu , Man-Chung Yue , Viet Anh Nguyen

Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When…

Computation and Language · Computer Science 2026-01-13 Nikhil Anand , Shwetha Somasundaram , Anirudh Phukan , Apoorv Saxena , Koyel Mukherjee

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

Despite the remarkable achievements of language models (LMs) across a broad spectrum of tasks, their propensity for generating toxic outputs remains a prevalent concern. Current solutions involving finetuning or auxiliary models usually…

Computation and Language · Computer Science 2024-08-13 Yu Li , Han Jiang , Chuanyang Gong , Zhihua Wei

Recent advances in mechanistic interpretability have revealed that large language models (LLMs) develop internal representations corresponding not only to concrete entities but also distinct, human-understandable abstract concepts and…

Machine Learning · Computer Science 2025-12-01 Rio Alexa Fear , Payel Mukhopadhyay , Michael McCabe , Alberto Bietti , Miles Cranmer

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…

Cryptography and Security · Computer Science 2026-03-26 Yuxiao Li , Alina Fastowski , Efstratios Zaradoukas , Bardh Prenkaj , Gjergji Kasneci

Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level…

Computation and Language · Computer Science 2026-03-31 Adi Shnaidman , Erin Feiglin , Osher Yaari , Efrat Mentel , Amit Levi , Raz Lapid

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…

Artificial Intelligence · Computer Science 2024-12-18 Zouying Cao , Yifei Yang , Hai Zhao

Understanding how large audio models represent music, and using that understanding to steer generation, is both challenging and underexplored. Inspired by mechanistic interpretability in language models, where direction vectors in…

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially…

Machine Learning · Computer Science 2026-02-17 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Y. Rogov , Ivan Oseledets , Elena Tutubalina
‹ Prev 1 3 4 5 6 7 10 Next ›