English
Related papers

Related papers: Evaluating Risks in Weak-to-Strong Alignment: A Bi…

200 papers

Flow matching has emerged as a powerful framework for generative modeling, with recent empirical successes highlighting the effectiveness of signal-space prediction ($x$-prediction). In this work, we investigate the transfer of this…

Machine Learning · Computer Science 2026-05-05 Jiadong Hong , Lei Liu , Xinyu Bian , Wenjie Wang , Zhaoyang Zhang

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the…

Machine Learning · Computer Science 2020-03-05 Leslie Rice , Eric Wong , J. Zico Kolter

A well-known problem when learning from user clicks are inherent biases prevalent in the data, such as position or trust bias. Click models are a common method for extracting information from user clicks, such as document relevance in web…

Information Retrieval · Computer Science 2024-12-17 Romain Deffayet , Philipp Hager , Jean-Michel Renders , Maarten de Rijke

Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model…

Computation and Language · Computer Science 2026-05-28 Eric Onyame , Runtao Zhou , Kowshik Thopalli , Bhavya Kailkhura , Chirag Agarwal

Reasoning with LLMs increasingly unfolds inside a broader verification loop. Internally, systems use cheap checks, such as self-consistency or proxy rewards, which we call weak verification. Externally, users inspect outputs and steer the…

Machine Learning · Computer Science 2026-02-20 Shayan Kiyani , Sima Noorani , George Pappas , Hamed Hassani

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

Machine Learning · Computer Science 2021-06-07 Robert-Florian Samoilescu , Arnaud Van Looveren , Janis Klaise

As AI adoption expands across human society, the problem of aligning AI models to match human preferences remains a grand challenge. Currently, the AI alignment field is deeply divided between behavioral and representational approaches,…

Computers and Society · Computer Science 2025-08-12 Ben Y. Reis , William La Cava

The past two decades have witnessed the great success of the algorithmic modeling framework advocated by Breiman et al. (2001). Nevertheless, the excellent prediction performance of these black-box models rely heavily on the availability of…

Machine Learning · Statistics 2021-06-04 Chengliang Tang , Gan Yuan , Tian Zheng

As machine learning models become increasingly prevalent in critical decision-making models and systems in fields like finance, healthcare, etc., ensuring their robustness against adversarial attacks and changes in the input data is…

Machine Learning · Statistics 2024-08-05 Arun Prakash R , Anwesha Bhattacharyya , Joel Vaughan , Vijayan N. Nair

Prediction of breakdown in disordered solids under external loading in a question of paramount importance. Here we use a fiber bundle model for disordered solids and record the time series of the avalanche sizes and energy bursts. The time…

Statistical Mechanics · Physics 2022-09-14 Diksha , Soumyajyoti Biswas

Multicalibration requires predicted scores to agree with label probabilities across rich families of subgroups and score-dependent tests, but existing methods require clean input-label pairs for evaluation and post-processing. This…

Machine Learning · Statistics 2026-05-12 Futoshi Futami , Takashi Ishida

We study generalization properties of weakly supervised learning. That is, learning where only a few "strong" labels (the actual target of our prediction) are present but many more "weak" labels are available. In particular, we show that…

Machine Learning · Computer Science 2020-02-21 Joshua Robinson , Stefanie Jegelka , Suvrit Sra

Despite significant research efforts, deep neural networks are still vulnerable to biases: this raises concerns about their fairness and limits their generalization. In this paper, we propose a bias-agnostic approach to mitigate the impact…

Machine Learning · Computer Science 2023-05-08 Rémi Nahon , Van-Tam Nguyen , Enzo Tartaglione

Self-training is a well-known approach for semi-supervised learning. It consists of iteratively assigning pseudo-labels to unlabeled data for which the model is confident and treating them as labeled examples. For neural networks, softmax…

Machine Learning · Computer Science 2024-04-04 Ambroise Odonnat , Vasilii Feofanov , Ievgen Redko

Recent research suggests that predictions made by machine-learning models can amplify biases present in the training data. When a model amplifies bias, it makes certain predictions at a higher rate for some groups than expected based on…

Machine Learning · Computer Science 2022-10-20 Melissa Hall , Laurens van der Maaten , Laura Gustafson , Maxwell Jones , Aaron Adcock

Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain…

Artificial Intelligence · Computer Science 2026-04-29 Inderjeet Nair , Jie Ruan , Lu Wang

Recent research has generated hope that inference scaling, such as resampling solutions until they pass verifiers like unit tests, could allow weaker models to match stronger ones. Beyond inference, this approach also enables training…

Machine Learning · Computer Science 2026-03-27 Benedikt Stroebl , Sayash Kapoor , Arvind Narayanan

Changepoint detection is commonly formulated by minimizing the sum of in-sample losses to quantify the model's overall fit. However, for flexible modeling procedures -- especially those involving high-dimensional parameter spaces or…

Methodology · Statistics 2026-05-05 Chengde Qian , Guanghui Wang , Zhaojun Wang , Changliang Zou

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…

Artificial Intelligence · Computer Science 2025-10-08 Qingyu Yin , Chak Tou Leong , Linyi Yang , Wenxuan Huang , Wenjie Li , Xiting Wang , Jaehong Yoon , YunXing , XingYu , Jinjin Gu

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

Machine Learning · Computer Science 2024-11-06 Junhao Dong , Xinghua Qu , Z. Jane Wang , Yew-Soon Ong