English
Related papers

Related papers: Learning from Negative Examples: Why Warning-Frame…

200 papers

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper presents a novel framework that leverages sparse autoencoders…

Machine Learning · Computer Science 2025-02-18 Zirui He , Haiyan Zhao , Yiran Qiao , Fan Yang , Ali Payani , Jing Ma , Mengnan Du

Background Study individuals may face repeated events overtime. However, there is no consensus around learning approaches to use in a high-dimensional framework for survival data (when the number of variables exceeds the number of…

Methodology · Statistics 2022-03-30 Juliette Murris , Anais Charles-Nelson , Audrey Lavenu , Sandrine Katsahian

The vast majority of theoretical results in machine learning and statistics assume that the available training data is a reasonably reliable reflection of the phenomena to be learned or estimated. Similarly, the majority of machine learning…

Machine Learning · Computer Science 2017-06-13 Moses Charikar , Jacob Steinhardt , Gregory Valiant

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Machine Learning · Computer Science 2020-10-14 Heinrich Jiang , Qijia Jiang , Aldo Pacchiano

We study a social learning scheme where at every time instant, each agent chooses to receive information from one of its neighbors at random. We show that under this sparser communication scheme, the agents learn the truth eventually and…

Multiagent Systems · Computer Science 2022-05-13 Yunus Inan , Mert Kayaalp , Emre Telatar , Ali H. Sayed

Regardless of the particular task we want them to perform in an environment, there are often shared safety constraints we want our agents to respect. For example, regardless of whether it is making a sandwich or clearing the table, a…

Machine Learning · Computer Science 2023-09-06 Konwoo Kim , Gokul Swamy , Zuxin Liu , Ding Zhao , Sanjiban Choudhury , Zhiwei Steven Wu

We show that language models' activations linearly encode when information was learned during training. Our setup involves creating a model with a known training order by sequentially fine-tuning Llama-3.2-1B on six disjoint but otherwise…

Machine Learning · Computer Science 2025-09-23 Dmitrii Krasheninnikov , Richard E. Turner , David Krueger

Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with learned refusal behaviors. We introduce Involuntary In-Context Learning (IICL), an…

Cryptography and Security · Computer Science 2026-04-22 Alex Polyakov , Daniel Kuznetsov

The problem of model collapse has presented new challenges in iterative training of generative models, where such training with synthetic data leads to an overall degradation of performance. This paper looks at the problem from a…

Machine Learning · Statistics 2026-02-19 Soham Bakshi , Sunrit Chakraborty

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos. Previous work suggests that representations can be disentangled if all but a few factors in the…

Deep-learning models can extract a rich assortment of features from data. Which features a model uses depends not only on \emph{predictivity} -- how reliably a feature indicates training-set labels -- but also on \emph{availability} -- how…

Machine Learning · Computer Science 2024-07-15 Katherine L. Hermann , Hossein Mobahi , Thomas Fel , Michael C. Mozer

Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train…

Machine Learning · Computer Science 2018-01-10 Cedric De Boom , Thomas Demeester , Bart Dhoedt

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

Machine Learning · Computer Science 2025-11-18 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

Recently, pretrained language models have shown state-of-the-art performance on the vulnerability detection task. These models are pretrained on a large corpus of source code, then fine-tuned on a smaller supervised vulnerability dataset.…

Machine Learning · Computer Science 2023-11-08 Benjamin Steenhoek , Md Mahbubur Rahman , Shaila Sharmin , Wei Le

Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…

Computation and Language · Computer Science 2024-10-08 Sarah Ball , Frauke Kreuter , Nina Panickssery

Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of…

Machine Learning · Computer Science 2025-03-18 Shengyuan Hu , Yiwei Fu , Zhiwei Steven Wu , Virginia Smith

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

Machine Learning · Computer Science 2022-10-26 Hong Liu , Sang Michael Xie , Zhiyuan Li , Tengyu Ma

Large language models with a huge number of parameters, when trained on near internet-sized number of tokens, have been empirically shown to obey neural scaling laws: specifically, their performance behaves predictably as a power law in…

Machine Learning · Computer Science 2022-11-01 Alexander Maloney , Daniel A. Roberts , James Sully

We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is likely to learn the bias information to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Byungju Kim , Hyunwoo Kim , Kyungsu Kim , Sungjin Kim , Junmo Kim