English
Related papers

Related papers: Understanding Emergent Misalignment via Feature Su…

200 papers

Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing…

Computation and Language · Computer Science 2026-02-02 Omar Mahmoud , Ali Khalil , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence. The scaling of these models, accomplished by increasing the number of parameters…

Machine Learning · Computer Science 2025-03-17 Leonardo Berti , Flavio Giorgi , Gjergji Kasneci

Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Nuoyan Zhou , Dawei Zhou , Decheng Liu , Nannan Wang , Xinbo Gao

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…

Computation and Language · Computer Science 2024-10-01 Sachin Kumar

Overfitting in deep learning has been the focus of a number of recent works, yet its exact impact on the behavior of neural networks is not well understood. This study analyzes overfitting by examining how the distribution of logits alters…

Machine Learning · Computer Science 2019-10-02 Zeju Li , Konstantinos Kamnitsas , Ben Glocker

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Computation and Language · Computer Science 2024-01-23 Pengyu Wang , Dong Zhang , Linyang Li , Chenkun Tan , Xinghao Wang , Ke Ren , Botian Jiang , Xipeng Qiu

Machine learning (ML) may be oblivious to human bias but it is not immune to its perpetuation. Marginalisation and iniquitous group representation are often traceable in the very data used for training, and may be reflected or even enhanced…

Machine Learning · Computer Science 2024-12-02 Stefano Sarao Mannelli , Federica Gerace , Negar Rostamzadeh , Luca Saglietti

Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, finetuning-based ones that compromise LLMs' safety alignment…

Cryptography and Security · Computer Science 2025-11-27 Zhixin Xie , Xurui Song , Jun Luo

We address a core problem of computer vision: Detection and description of 2D feature points for image matching. For a long time, hand-crafted designs, like the seminal SIFT algorithm, were unsurpassed in accuracy and efficiency. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Aritra Bhowmik , Stefan Gumhold , Carsten Rother , Eric Brachmann

Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. However, existing methods are brittle in practice and can…

Machine Learning · Computer Science 2025-04-08 Kevin Kuo , Amrith Setlur , Kartik Srinivas , Aditi Raghunathan , Virginia Smith

Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis. Autoencoder neural networks learn to reconstruct normal images, and hence…

Machine Learning · Computer Science 2019-01-21 Laura Beggel , Michael Pfeiffer , Bernd Bischl

Reinforcement learning (RL) yields substantial improvements in large language models (LLMs) downstream task performance and alignment with human values. Surprisingly, such large gains result from updating only a small subnetwork comprising…

Machine Learning · Computer Science 2025-12-19 Sagnik Mukherjee , Lifan Yuan , Dilek Hakkani-Tur , Hao Peng

Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from…

Neural and Evolutionary Computing · Computer Science 2017-11-21 Hesham Mostafa , Vishwajith Ramesh , Gert Cauwenberghs

Large language models (LLMs) are advanced AI systems applied across various domains, including NLP, information retrieval, and recommendation systems. Despite their adaptability and efficiency, LLMs have not been extensively explored for…

Artificial Intelligence · Computer Science 2025-07-08 Harshith Manjunath , Lucas Heublein , Tobias Feigl , Felix Ott

Why is safety alignment in LLMs shallow? We prove that gradient-based alignment inherently concentrates on positions where harm is decided and vanishes beyond. Using a martingale decomposition of sequence-level harm, we derive an exact…

Machine Learning · Computer Science 2026-03-06 Robin Young

Symmetries play a central role in physics, organizing dynamics, constraining interactions, and determining the effective number of physical degrees of freedom. In parallel, modern artificial intelligence methods have demonstrated a…

High Energy Physics - Phenomenology · Physics 2026-02-03 Veronica Sanz

This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-critical applications where ensuring fairness is of paramount…

Software Engineering · Computer Science 2022-02-15 Saeid Tizpaz-Niari , Ashish Kumar , Gang Tan , Ashutosh Trivedi

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Machine Learning · Computer Science 2026-03-24 Guangnian Wan , Xinyin Ma , Gongfan Fang , Xinchao Wang

LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dramatically shift behavior outside those contexts. In one experiment, we finetune…

Computation and Language · Computer Science 2025-12-11 Jan Betley , Jorio Cocola , Dylan Feng , James Chua , Andy Arditi , Anna Sztyber-Betley , Owain Evans

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

Computation and Language · Computer Science 2025-07-15 Itay Itzhak , Yonatan Belinkov , Gabriel Stanovsky
‹ Prev 1 8 9 10 Next ›