English
Related papers

Related papers: Safety Reasoning with Guidelines

200 papers

In this paper, we focus on the out-of-distribution (OOD) generalization of self-supervised learning (SSL). By analyzing the mini-batch construction during the SSL training phase, we first give one plausible explanation for SSL having OOD…

Machine Learning · Computer Science 2025-05-23 Wenwen Qiang , Jingyao Wang , Zeen Song , Jiangmeng Li , Changwen Zheng

Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reasoning via chain-of-thought (CoT) prompting or…

Machine Learning · Computer Science 2026-03-18 Robert Welch , Emir Konuk , Kevin Smith

Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic…

Machine Learning · Computer Science 2023-10-31 Marc Rigter , Bruno Lacerda , Nick Hawes

The increasing reliance on large language models (LLMs) for diverse applications necessitates a thorough understanding of their robustness to adversarial perturbations and out-of-distribution (OOD) inputs. In this study, we investigate the…

Computation and Language · Computer Science 2024-12-17 April Yang , Jordan Tab , Parth Shah , Paul Kotchavong

Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these…

Computation and Language · Computer Science 2025-05-01 Canaan Yung , Hadi Mohaghegh Dolatabadi , Sarah Erfani , Christopher Leckie

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Cryptography and Security · Computer Science 2025-10-10 Man Hu , Xinyi Wu , Zuofeng Suo , Jinbo Feng , Linghui Meng , Yanhao Jia , Anh Tuan Luu , Shuai Zhao

Deep neural networks (DNNs) have become the de facto learning mechanism in different domains. Their tendency to perform unreliably on out-of-distribution (OOD) inputs hinders their adoption in critical domains. Several approaches have been…

Machine Learning · Computer Science 2020-06-26 Vahdat Abdelzad , Krzysztof Czarnecki , Rick Salay

Supervised Fine-Tuning (SFT) on long Chain-of-Thought (CoT) trajectories has become a pivotal phase in building large reasoning models. However, how CoT trajectories from different sources influence the generalization performance of models…

Computation and Language · Computer Science 2026-04-07 Zhaoyi Li , Xiangyu Xi , Zhengyu Chen , Wei Wang , Gangwei Jiang , Ranran Shen , Linqi Song , Ying Wei , Defu Lian

Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent…

Machine Learning · Computer Science 2024-05-09 Akifumi Wachi , Xun Shen , Yanan Sui

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

We study the problem of out-of-distribution dynamics (OODD) detection, which involves detecting when the dynamics of a temporal process change compared to the training-distribution dynamics. This is relevant to applications in control,…

Machine Learning · Computer Science 2022-05-25 Mohamad H Danesh , Alan Fern

Out-of-distribution (OOD) generalization is a challenging machine learning problem yet highly desirable in many high-stake applications. Existing methods suffer from overly pessimistic modeling with low generalization confidence. As…

Machine Learning · Computer Science 2024-06-10 Fengchun Qiao , Xi Peng

As training datasets grow larger, we aspire to develop models that generalize well to any diverse test distribution, even if the latter deviates significantly from the training data. Various approaches like domain adaptation, domain…

Machine Learning · Computer Science 2024-10-10 Andreas Loukas , Karolis Martinkus , Ed Wagstaff , Kyunghyun Cho

Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Yulei Qin , Gang Li , Zongyi Li , Zihan Xu , Yuchen Shi , Zhekai Lin , Xiao Cui , Ke Li , Xing Sun

In this work, we study out-of-distribution (OOD) generalization in meta-reinforcement learning from an information-theoretic perspective. We begin by establishing OOD generalization bounds for meta-supervised learning under two distinct…

Machine Learning · Computer Science 2026-04-07 Xingtu Liu

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the model making biased…

Machine Learning · Computer Science 2023-10-11 Bhavya Vasudeva , Kameron Shahabi , Vatsal Sharan

Detecting out-of-distribution (OOD) samples is vital for developing machine learning based models for critical safety systems. Common approaches for OOD detection assume access to some OOD samples during training which may not be available…

Machine Learning · Computer Science 2021-10-19 Koby Bibas , Meir Feder , Tal Hassner

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Machine Learning · Computer Science 2024-05-16 Xingzhou Lou , Junge Zhang , Ziyan Wang , Kaiqi Huang , Yali Du

The safety of large language models (LLMs) relies on alignment techniques such as reinforcement learning from human feedback (RLHF). However, recent theoretical analyses suggest that reinforcement learning-based training does not acquire…

Machine Learning · Computer Science 2026-04-06 Haruhi Shida , Koo Imai , Keigo Kansa

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs)…

Cryptography and Security · Computer Science 2025-06-06 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Zachary Yahn , Yichang Xu , Ling Liu