English
Related papers

Related papers: Conceptors for Semantic Steering

200 papers

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

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Cryptography and Security · Computer Science 2025-09-29 Xiyu Zeng , Siyuan Liang , Liming Lu , Haotian Zhu , Enguang Liu , Jisheng Dang , Yongbin Zhou , Shuchao Pang

Controlling specific behaviors in large language models while preserving their general capabilities is a central challenge for safe and reliable artificial intelligence deployment. Current steering methods, such as vector addition and…

Machine Learning · Computer Science 2025-10-31 Hieu M. Vu , Tan M. Nguyen

Test-time compute has emerged as a key paradigm for enhancing LLM reasoning, yet prevailing approaches like Best-of-N and majority voting apply uniform depth across inputs, wasting computation on simple queries while potentially…

Artificial Intelligence · Computer Science 2025-09-30 Yixin He , Lumingyuan Tang

Concept-based interpretations of black-box models are often more intuitive for humans to understand. The most widely adopted approach for concept-based interpretation is Concept Activation Vector (CAV). CAV relies on learning a linear…

Machine Learning · Computer Science 2024-02-07 Andrew Bai , Chih-Kuan Yeh , Pradeep Ravikumar , Neil Y. C. Lin , Cho-Jui Hsieh

Object skeletons offer a concise representation of structural information, capturing essential aspects of posture and orientation that are crucial for autonomous driving applications. However, a unified architecture that simultaneously…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Yasamin Borhani , Taylor Mordan , Yihan Wang , Reyhaneh Hosseininejad , Javad Khoramdel , Alexandre Alahi

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based…

Computation and Language · Computer Science 2025-03-05 Zhengxuan Wu , Aryaman Arora , Atticus Geiger , Zheng Wang , Jing Huang , Dan Jurafsky , Christopher D. Manning , Christopher Potts

Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However, despite its empirical success, it currently lacks a…

Machine Learning · Computer Science 2026-05-08 Tatiana Gaintseva , Andrew Stepanov , Ziquan Liu , Martin Benning , Gregory Slabaugh , Jiankang Deng , Ismail Elezi

Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention…

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

Inverting corrupted images into the latent space of diffusion models is challenging. Current methods, which encode an image into a single latent vector, struggle to balance structural fidelity with semantic accuracy, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Yichen Wu , Xu Liu , Chenxuan Zhao , Xinyu Wu

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing…

Computation and Language · Computer Science 2026-05-29 Yingdong Shi , Ruiming Zhang , Changming Li , Zhiyu Yang , Kaixing Zhang , Jingyi Yu , Kan Ren

Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By…

Artificial Intelligence · Computer Science 2026-05-05 Xinyan Jiang , Ninghao Liu , Di Wang , Lijie Hu

Large Multimodal Models (LMMs) have recently demonstrated their proficiency in holistic visual comprehension. However, most of them struggle to tackle region-level perception guided by visual prompts, especially for cases where multiple…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yun Xing , Hanyuan Liu , Jiahao Nie , Shijian Lu

Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Javier Ferrando , Enrique Lopez-Cuena , Pablo Agustin Martin-Torres , Daniel Hinjos , Anna Arias-Duart , Dario Garcia-Gasulla

Generative concept bottleneck models aim to enable interpretable generation by routing synthesis through explicit, user-facing concepts. In practice, prior approaches often rely on non-explicit bottleneck representations (e.g., vision cues…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Sangwon Kim , Kyoungoh Lee , Jeyoun Dong , Kwang-Ju Kim

Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled…

Sound · Computer Science 2026-04-07 Xunyi Jiang , Mingyang Yao , Jingyue Huang , Julian McAuley

Latent reasoning compresses the chain-of-thought (CoT) into continuous hidden states, yet existing methods rely on dense latent transitions that remain difficult to interpret and control. Meanwhile, sparse representation models uncover…

Artificial Intelligence · Computer Science 2026-02-03 Yadong Wang , Haodong Chen , Yu Tian , Chuanxing Geng , Dong Liang , Xiang Chen

Trajectory generation has garnered significant attention from researchers in the field of spatio-temporal analysis, as it can generate substantial synthesized human mobility trajectories that enhance user privacy and alleviate data…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Ji Cao , Tongya Zheng , Qinghong Guo , Yu Wang , Junshu Dai , Shunyu Liu , Jie Yang , Jie Song , Mingli Song

Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence…

Artificial Intelligence · Computer Science 2026-02-13 Xin Xu , Tong Yu , Xiang Chen , Haoliang Wang , Julian McAuley , Saayan Mitra