English
Related papers

Related papers: Safety Reasoning with Guidelines

200 papers

The safety of learning-enabled cyber-physical systems is compromised by the well-known vulnerabilities of deep neural networks to out-of-distribution (OOD) inputs. Existing literature has sought to monitor the safety of such systems by…

Machine Learning · Computer Science 2025-04-21 Vivian Lin , Ramneet Kaur , Yahan Yang , Souradeep Dutta , Yiannis Kantaros , Anirban Roy , Susmit Jha , Oleg Sokolsky , Insup Lee

Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this…

Artificial Intelligence · Computer Science 2026-05-29 Shaojie Wang , Liang Zhang

Reinforcement learning (RL) in the real world necessitates the development of procedures that enable agents to explore without causing harm to themselves or others. The most successful solutions to the problem of safe RL leverage offline…

Machine Learning · Computer Science 2025-01-09 Alexander Quessy , Thomas Richardson , Sebastian East

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during…

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…

Computation and Language · Computer Science 2025-09-03 Xiaomin Li , Zhou Yu , Zhiwei Zhang , Xupeng Chen , Ziji Zhang , Yingying Zhuang , Narayanan Sadagopan , Anurag Beniwal

Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test data without access to labels. However, this reliance on…

Machine Learning · Computer Science 2026-03-17 Vanshaj Khattar , Md Rafi ur Rashid , Moumita Choudhury , Jing Liu , Toshiaki Koike-Akino , Ming Jin , Ye Wang

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Artificial Intelligence · Computer Science 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…

Computation and Language · Computer Science 2025-04-15 Shaoqing Zhang , Zhuosheng Zhang , Kehai Chen , Rongxiang Weng , Muyun Yang , Tiejun Zhao , Min Zhang

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…

Computation and Language · Computer Science 2025-05-26 Youliang Yuan , Wenxiang Jiao , Wenxuan Wang , Jen-tse Huang , Jiahao Xu , Tian Liang , Pinjia He , Zhaopeng Tu

Building object detectors that are robust to domain shifts is critical for real-world applications. Prior approaches fine-tune a pre-trained backbone and risk overfitting it to in-distribution (ID) data and distorting features useful for…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Kuniaki Saito , Donghyun Kim , Piotr Teterwak , Rogerio Feris , Kate Saenko

Ensuring the safety of reinforcement learning (RL) algorithms is crucial to unlock their potential for many real-world tasks. However, vanilla RL and most safe RL approaches do not guarantee safety. In recent years, several methods have…

Machine Learning · Computer Science 2023-11-21 Hanna Krasowski , Jakob Thumm , Marlon Müller , Lukas Schäfer , Xiao Wang , Matthias Althoff

Inductive reasoning, a cornerstone of human cognition, enables generalization from limited data but hasn't yet been fully achieved by large language models (LLMs). While modern LLMs excel at reasoning tasks, their ability to maintain stable…

Artificial Intelligence · Computer Science 2025-05-29 Chunyang Li , Weiqi Wang , Tianshi Zheng , Yangqiu Song

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

Computation and Language · Computer Science 2024-11-27 Tim Hartill

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper,…

Artificial Intelligence · Computer Science 2026-05-05 Jianan Chen , Zhifang Zhang , Shuo He , Linan Yue , Lei Feng , Minling Zhang

Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promising new alignment paradigm to mitigate such failures by…

Machine Learning · Computer Science 2026-05-22 Andy Han , Kristina Fujimoto , Avidan Shah , Kiet Nguyen , Kai Xu , Chen Yueh-Han , Ilia Sucholutsky , Rico Angell

This dissertation investigates how reinforcement learning (RL) methods can be designed to be safe, sample-efficient, and robust. Framed through the unifying perspective of contextual-bandit RL, the work addresses two major application…

Machine Learning · Computer Science 2025-10-20 Shashank Gupta

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Large reasoning models (LRMs) have significantly advanced performance on complex tasks, yet their tendency to overthink introduces inefficiencies. This study investigates the internal mechanisms of reinforcement learning (RL)-trained LRMs…

Artificial Intelligence · Computer Science 2025-05-22 Rongzhi Zhu , Yi Liu , Zequn Sun , Yiwei Wang , Wei Hu

The usage of deep neural networks in safety-critical systems is limited by our ability to guarantee their correct behavior. Runtime monitors are components aiming to identify unsafe predictions and discard them before they can lead to…

Machine Learning · Computer Science 2023-01-16 Joris Guérin , Kevin Delmas , Raul Sena Ferreira , Jérémie Guiochet

The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…

Computation and Language · Computer Science 2025-05-27 Zhihong Pan , Kai Zhang , Yuze Zhao , Yupeng Han
‹ Prev 1 8 9 10 Next ›