English
Related papers

Related papers: RepIt: Steering Language Models with Concept-Speci…

200 papers

Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing methods, whether rule-based or data-driven, frequently struggle to capture complex scene…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Kefei Tian , Yuansheng Lian , Kai Yang , Xiangdong Chen , Shen Li

Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new approach utilizing samples of contrasting inputs to detect…

Artificial Intelligence · Computer Science 2025-02-26 Lukasz Bartoszcze , Sarthak Munshi , Bryan Sukidi , Jennifer Yen , Zejia Yang , David Williams-King , Linh Le , Kosi Asuzu , Carsten Maple

We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we…

Artificial Intelligence · Computer Science 2025-10-17 Vincent Siu , Nicholas Crispino , David Park , Nathan W. Henry , Zhun Wang , Yang Liu , Dawn Song , Chenguang Wang

The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model's output, hoping for a responsive model that can complete responses according to their…

Computation and Language · Computer Science 2024-07-25 Jianhao Yan , Yun Luo , Yue Zhang

Recent work on domain-specific reasoning with large language models (LLMs) often relies on training-intensive approaches that require parameter updates. While activation steering has emerged as a parameter efficient alternative, existing…

Artificial Intelligence · Computer Science 2026-01-21 Wencheng Ye , Xiaoyang Yuan , Yi Bin , Pengpeng Zeng , Hengyu Jin , Liang Peng , Heng Tao Shen

The era of Large Language Models (LLMs) raises new demands for automatic evaluation metrics, which should be adaptable to various application scenarios while maintaining low cost and effectiveness. Traditional metrics for automatic text…

Computation and Language · Computer Science 2024-10-29 Shuqian Sheng , Yi Xu , Tianhang Zhang , Zanwei Shen , Luoyi Fu , Jiaxin Ding , Lei Zhou , Xiaoying Gan , Xinbing Wang , Chenghu Zhou

Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests, yet the same blanket safeguards also block legitimate uses in policing, defense, and other high-stakes settings. Earlier "refusal-direction" edits…

Machine Learning · Computer Science 2025-09-17 Xin Tong , Zhi Lin , Jingya Wang , Meng Han , Bo Jin

Object hallucination critically undermines the reliability of Multimodal Large Language Models, often stemming from a fundamental failure in cognitive introspection, where models blindly trust linguistic priors over specific visual…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Shuliang Liu , Songbo Yang , Dong Fang , Sihang Jia , Yuqi Tang , Lingfeng Su , Ruoshui Peng , Yibo Yan , Xin Zou , Xuming Hu

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…

Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on…

Computation and Language · Computer Science 2026-02-20 Takyoung Kim , Jinseok Nam , Chandrayee Basu , Xing Fan , Chengyuan Ma , Heng Ji , Gokhan Tur , Dilek Hakkani-Tür

Safety alignment in large language models (LLMs) induces over-refusals -- where LLMs decline benign requests due to aggressive safety filters. We analyze this phenomenon in retrieval-augmented generation (RAG), where both the query intent…

Computation and Language · Computer Science 2025-10-14 Utsav Maskey , Mark Dras , Usman Naseem

Evaluating large language models (LLMs) on comprehensive benchmarks is a cornerstone of their development, yet it's often computationally and financially prohibitive. While Item Response Theory (IRT) offers a promising path toward…

Artificial Intelligence · Computer Science 2025-10-07 Lele Liao , Qile Zhang , Ruofan Wu , Guanhua Fang

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Computation and Language · Computer Science 2025-04-15 Alessandro Stolfo , Vidhisha Balachandran , Safoora Yousefi , Eric Horvitz , Besmira Nushi

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…

Cryptography and Security · Computer Science 2026-01-29 Xianglin Yang , Gelei Deng , Jieming Shi , Tianwei Zhang , Jin Song Dong

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Yunqing Zhao , Tianyu Pang , Chao Du , Xiao Yang , Chongxuan Li , Ngai-Man Cheung , Min Lin

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Computation and Language · Computer Science 2025-10-27 Bushra Sabir , Yansong Gao , Alsharif Abuadbba , M. Ali Babar

As large language models (LLMs) are increasingly deployed in enterprise settings, controlling model behavior based on user roles becomes an essential requirement. Existing safety methods typically assume uniform access and focus on…

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied,…

Machine Learning · Computer Science 2026-02-09 Navita Goyal , Hal Daumé

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

Computation and Language · Computer Science 2025-02-07 Dang Huu-Tien , Trung-Tin Pham , Hoang Thanh-Tung , Naoya Inoue

Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Mansi Phute , Ravikumar Balakrishnan
‹ Prev 1 4 5 6 7 8 10 Next ›