English
Related papers

Related papers: Efficient Switchable Safety Control in LLMs via Ma…

200 papers

We present an innovative multi-stage optimization strategy combining reinforcement learning (RL) and supervised fine-tuning (SFT) to enhance the pedagogical knowledge of large language models (LLMs), as illustrated by EduQwen 32B-RL1,…

Computation and Language · Computer Science 2026-04-09 Navan Preet Singh , Xiaokun Wang , Anurag Garikipati , Madalina Ciobanu , Qingqing Mao , Ritankar Das

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Computation and Language · Computer Science 2025-08-27 Junjie Ye , Yilong Wu , Sixian Li , Yuming Yang , Zhiheng Xi , Tao Gui , Qi Zhang , Xuanjing Huang , Peng Wang , Zhongchao Shi , Jianping Fan , Zhengyin Du

Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. However, standard SFT uniformly penalizes all tokens,…

Computation and Language · Computer Science 2025-10-14 Zhiwen Ruan , Yixia Li , He Zhu , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

Machine Learning · Computer Science 2026-04-28 Bilgehan Sel , Vaishakh Keshava , Phillip Wallis , Lukas Rutishauser , Ming Jin , Dingcheng Li

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…

Cryptography and Security · Computer Science 2025-05-26 Weiyang Guo , Jing Li , Wenya Wang , YU LI , Daojing He , Jun Yu , Min Zhang

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face…

Computation and Language · Computer Science 2025-03-05 Jingyu Zhang , Ahmed Elgohary , Ahmed Magooda , Daniel Khashabi , Benjamin Van Durme

Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combines Large Language Models (LLMs), numerical optimization, and…

Systems and Control · Electrical Eng. & Systems 2025-05-08 Xiyu Deng , Quan Khanh Luu , Anh Van Ho , Yorie Nakahira

As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes safety will cause users to feel less engaged and assisted…

Computation and Language · Computer Science 2024-04-02 Yi-Lin Tuan , Xilun Chen , Eric Michael Smith , Louis Martin , Soumya Batra , Asli Celikyilmaz , William Yang Wang , Daniel M. Bikel

Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces…

Computation and Language · Computer Science 2025-12-02 Jinghan Jia , Nathalie Baracaldo , Sijia Liu

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables…

Computation and Language · Computer Science 2026-05-26 Michael Orme , Yanchao Yu , Zhiyuan Tan

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

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

Machine Learning · Statistics 2025-03-28 Pin-Yu Chen , Han Shen , Payel Das , Tianyi Chen

By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequentially to the pretrained model. Because SFT and alignment…

Computation and Language · Computer Science 2026-05-11 Zhichao Wang , Bin Bi , Zixu Zhu , Xiangbo Mao , Jun Wang , Shiyu Wang , Cheng Wang , Dong Nie , Lingzi Hong

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Computation and Language · Computer Science 2023-10-03 Tianci Xue , Ziqi Wang , Heng Ji

Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs…

Computation and Language · Computer Science 2025-04-07 Abhishek Singhania , Christophe Dupuy , Shivam Mangale , Amani Namboori

The increasing penetration of renewable generation and the growing variability of electrified demand introduce substantial operational uncertainty to modern power systems. Topology reconfiguration is widely recognized as an effective and…

Systems and Control · Electrical Eng. & Systems 2026-03-17 Zongyan Zhang , Chao Shen , Xu Wan , Jie Song , Mingyang Sun

Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…

Computation and Language · Computer Science 2025-02-14 Jingxin Xu , Guoshun Nan , Sheng Guan , Sicong Leng , Yilian Liu , Zixiao Wang , Yuyang Ma , Zhili Zhou , Yanzhao Hou , Xiaofeng Tao