English
Related papers

Related papers: Understanding Emergent Misalignment via Feature Su…

200 papers

The paper investigates the performance of state-of-the-art low-parameter deep neural networks for computer vision, focusing on bottleneck architectures and their behavior using superlinear activation functions. We address interference in…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Lilian Hollard , Lucas Mohimont , Nathalie Gaveau , Luiz-Angelo Steffenel

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Computation and Language · Computer Science 2025-11-18 Dongyoon Hahm , Taywon Min , Woogyeol Jin , Kimin Lee

Finding semantic correspondences is a challenging problem. With the breakthrough of CNNs stronger features are available for tasks like classification but not specifically for the requirements of semantic matching. In the following we…

Computer Vision and Pattern Recognition · Computer Science 2019-06-18 Nikolai Ufer , Kam To Lui , Katja Schwarz , Paul Warkentin , Björn Ommer

A central idea in mechanistic interpretability is that neural networks represent more features than they have dimensions, arranging them in superposition to form an over-complete basis. This framing has been influential, motivating…

Machine Learning · Computer Science 2026-03-11 Lucas Prieto , Edward Stevinson , Melih Barsbey , Tolga Birdal , Pedro A. M. Mediano

We discover the emergence of \textit{basins} in the loss landscape of large language models. As model scale increases, LLMs become progressively more resilient to random perturbations in the parameter space, giving rise to expansive…

Machine Learning · Computer Science 2026-03-17 Huanran Chen , Yinpeng Dong , Zeming Wei , Yao Huang , Yichi Zhang , Hang Su , Jun Zhu

The advancement of Large Language Models (LLMs) for domain applications in fields such as materials science and engineering depends on the development of fine-tuning strategies that adapt models for specialized, technical capabilities. In…

Computation and Language · Computer Science 2024-09-06 Wei Lu , Rachel K. Luu , Markus J. Buehler

We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical question arises here:…

Computation and Language · Computer Science 2024-12-24 Minlie Huang , Yingkang Wang , Shiyao Cui , Pei Ke , Jie Tang

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…

Computation and Language · Computer Science 2024-12-12 Yuxiao Lu , Arunesh Sinha , Pradeep Varakantham

Prior work shows that fine-tuning aligned models on benign data degrades safety in text and vision modalities, and that proximity to harmful content in representation space predicts which samples cause the most damage. However, existing…

Cryptography and Security · Computer Science 2026-04-21 Jaechul Roh , Amir Houmansadr

Many modern machine learning models are trained to achieve zero or near-zero training error in order to obtain near-optimal (but non-zero) test error. This phenomenon of strong generalization performance for "overfitted" / interpolated…

Machine Learning · Statistics 2018-10-29 Mikhail Belkin , Daniel Hsu , Partha Mitra

Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts…

Machine Learning · Computer Science 2025-07-29 Gabriel J. Perin , Runjin Chen , Xuxi Chen , Nina S. T. Hirata , Zhangyang Wang , Junyuan Hong

Regular mammography screening is essential for early breast cancer detection. Deep learning-based risk prediction methods have sparked interest to adjust screening intervals for high-risk groups. While early methods focused only on current…

Image and Video Processing · Electrical Eng. & Systems 2025-06-25 Solveig Thrun , Stine Hansen , Zijun Sun , Nele Blum , Suaiba A. Salahuddin , Kristoffer Wickstrøm , Elisabeth Wetzer , Robert Jenssen , Maik Stille , Michael Kampffmeyer

Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be diverse, introducing safety concerns regarding the potential…

Computation and Language · Computer Science 2024-10-15 Hyeong Kyu Choi , Xuefeng Du , Yixuan Li

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…

Computation and Language · Computer Science 2026-02-25 Yanbo Dai , Zhenlan Ji , Zongjie Li , Shuai Wang

Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to…

Machine Learning · Computer Science 2025-10-14 Edward Stevinson , Lucas Prieto , Melih Barsbey , Tolga Birdal

Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent Multimodal Large Language Models (MLLMs) have demonstrated…

Computation and Language · Computer Science 2026-04-29 Xiangxiang Zhang , Caijun Jia , Siyuan Li , Dingyu He , Xiya Xiong , Zheng Sun , Honghao He , Yuchen Wu , Bihui Yu , Linzhuang Sun , Cheng Tan , Jingxuan Wei

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to…

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Computation and Language · Computer Science 2024-10-16 Yihuai Hong , Yuelin Zou , Lijie Hu , Ziqian Zeng , Di Wang , Haiqin Yang

Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth interpretation of the fine-tuning process through circuit…

Computation and Language · Computer Science 2025-06-16 Xu Wang , Yan Hu , Wenyu Du , Reynold Cheng , Benyou Wang , Difan Zou