English
Related papers

Related papers: Minimizing Collateral Damage in Activation Steerin…

200 papers

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…

Computation and Language · Computer Science 2025-07-22 Anirudh Sundar , Sinead Williamson , Katherine Metcalf , Barry-John Theobald , Skyler Seto , Masha Fedzechkina

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…

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

Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model…

Computation and Language · Computer Science 2024-06-25 Asa Cooper Stickland , Alexander Lyzhov , Jacob Pfau , Salsabila Mahdi , Samuel R. Bowman

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

Activation steering offers a computationally efficient mechanism for controlling Large Language Models (LLMs) without fine-tuning. While effectively controlling target traits (e.g., persona), coherency degradation remains a major obstacle…

Computation and Language · Computer Science 2026-05-29 Yoshihiro Izawa , Gouki Minegishi , Koshi Eguchi , Sosuke Hosokawa , Kenjiro Taura

Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often…

Computation and Language · Computer Science 2026-05-18 Sasha Cui , Zhongren Chen

Inference-time steering offers a promising way to control language models (LMs) without retraining. However, standard approaches typically rely on activation addition, which inevitably alters the hidden-state magnitudes raising concerns…

Machine Learning · Computer Science 2026-05-19 Zejia You , Chunyuan Deng , Hanjie Chen

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

This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text…

Computation and Language · Computer Science 2024-02-05 Kai Konen , Sophie Jentzsch , Diaoulé Diallo , Peer Schütt , Oliver Bensch , Roxanne El Baff , Dominik Opitz , Tobias Hecking

Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified…

Biomolecules · Quantitative Biology 2025-09-15 Long-Kai Huang , Rongyi Zhu , Bing He , Jianhua Yao

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key…

Computation and Language · Computer Science 2026-05-15 Diancheng Kang , Zheyuan Liu , Ningshan Ma , Yue Huang , Zhaoxuan Tan , Meng Jiang

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

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

Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode and ground distinct visual concepts remain poorly understood. To bridge this gap, we propose…

Artificial Intelligence · Computer Science 2026-05-08 Zehao Deng , Tianjie Ju , Zheng Wu , Liangbo He , Jun Lan , Huijia Zhu , Weiqiang Wang , Zhuosheng Zhang

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

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

Reliable behavior control is central to deploying large language models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches…

Artificial Intelligence · Computer Science 2025-11-19 Manjiang Yu , Hongji Li , Priyanka Singh , Xue Li , Di Wang , Lijie Hu

Prompt engineering and finetuning aim to maximize language model performance on a given metric (like toxicity reduction). However, these methods do not fully elicit a model's capabilities. To reduce this gap, we introduce activation…

Computation and Language · Computer Science 2024-10-11 Alexander Matt Turner , Lisa Thiergart , Gavin Leech , David Udell , Juan J. Vazquez , Ulisse Mini , Monte MacDiarmid

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

Computation and Language · Computer Science 2025-09-05 Dani Roytburg , Matthew Bozoukov , Matthew Nguyen , Jou Barzdukas , Simon Fu , Narmeen Oozeer
‹ Prev 1 3 4 5 6 7 10 Next ›