English
Related papers

Related papers: SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthet…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). To address the lack of verification signals at test time, prior studies…

Computation and Language · Computer Science 2025-10-17 Wenkai Yang , Weijie Liu , Ruobing Xie , Yiju Guo , Lulu Wu , Saiyong Yang , Yankai Lin

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning…

Artificial Intelligence · Computer Science 2026-05-08 Xiaomin Li , Jianheng Hou , Zheyuan Deng , Zhiwei Zhang , Taoran Li , Binghang Lu , Bing Hu , Yunhan Zhao , Yuexing Hao

Triangular tethered formation system (TTFS) provide a promising platform for deep space exploration and distributed sensing due to its intrinsic spatial-orientation stability and capability of adjusting distances among node satellites…

Systems and Control · Electrical Eng. & Systems 2026-01-09 Xinyi Tao , Panfeng Huang , Fan Zhang

Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively. In this work, we investigate how synthesized RL data can further improve…

Machine Learning · Computer Science 2025-06-04 Zijian Wu , Jinjie Ni , Xiangyan Liu , Zichen Liu , Hang Yan , Michael Qizhe Shieh

Generating step-by-step "chain-of-thought" rationales improves language model performance on complex reasoning tasks like mathematics or commonsense question-answering. However, inducing language model rationale generation currently…

Machine Learning · Computer Science 2022-05-23 Eric Zelikman , Yuhuai Wu , Jesse Mu , Noah D. Goodman

Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic…

Robotics · Computer Science 2026-04-13 Zukun Zhang , Kai Shu , Mingqiao Mo

Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical…

Computation and Language · Computer Science 2026-04-24 Aladin Djuhera , Swanand Ravindra Kadhe , Farhan Ahmed , Syed Zawad , Holger Boche

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Kexin Tang , Chao Yang , Fuying Ye , Yu Qiao , Yiming Qian

When users seek social support from chatbots, they disclose their situation gradually, yet most evaluations of supportive LLMs rely on single-turn, fully specified prompts. We introduce a multi-turn simulation framework that closes this…

Computation and Language · Computer Science 2026-04-21 Michelle Star , Andrew Aquilina , Yu-Ru Lin

Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not…

Machine Learning · Computer Science 2020-05-28 Koorosh Aslansefat , Ioannis Sorokos , Declan Whiting , Ramin Tavakoli Kolagari , Yiannis Papadopoulos

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually…

Machine Learning · Computer Science 2025-10-16 Anna Hedström , Salim I. Amoukou , Tom Bewley , Saumitra Mishra , Manuela Veloso

Multi-turn interactions with language models (LMs) pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and…

Cryptography and Security · Computer Science 2025-08-26 Salman Rahman , Liwei Jiang , James Shiffer , Genglin Liu , Sheriff Issaka , Md Rizwan Parvez , Hamid Palangi , Kai-Wei Chang , Yejin Choi , Saadia Gabriel

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

The performance of Large Vision Language Models (LVLMs) is dependent on the size and quality of their training datasets. Existing video instruction tuning datasets lack diversity as they are derived by prompting large language models with…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Orr Zohar , Xiaohan Wang , Yonatan Bitton , Idan Szpektor , Serena Yeung-Levy

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Machine Learning · Computer Science 2026-03-17 Ming Wen , Kun Yang , Xin Chen , Jingyu Zhang , Dingding Han , Shiwen Cui , Yuedong Xu

There has been a recent surge in single-step adversarial training as it shows robustness and efficiency. However, a phenomenon referred to as ``catastrophic overfitting" has been observed, which is prevalent in single-step defenses and may…

Machine Learning · Computer Science 2022-10-12 Zhuorong Li , Daiwei Yu

Safe Reinforcement Learning (SafeRL) is the subfield of reinforcement learning that explicitly deals with safety constraints during the learning and deployment of agents. This survey provides a mathematically rigorous overview of SafeRL…

Machine Learning · Computer Science 2026-04-30 Ankita Kushwaha , Kiran Ravish , Preeti Lamba , Pawan Kumar

Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…

Software Engineering · Computer Science 2026-04-03 Tyler Slater