English
Related papers

Related papers: PKU-SafeRLHF: Towards Multi-Level Safety Alignment…

200 papers

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective…

Computation and Language · Computer Science 2024-12-17 Tao Zhang , Ziqian Zeng , Yuxiang Xiao , Huiping Zhuang , Cen Chen , James Foulds , Shimei Pan

Reinforcement Learning from Human Feedback (RLHF) can reveal implicit objectives such as safety considerations that go beyond task completion. In this work, we focus on the common safety criteria embedded in crowd preference datasets, where…

Artificial Intelligence · Computer Science 2026-05-22 Qian Lin , Daniel S. Brown

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

Large Language Models (LLMs), when used in educational settings without pedagogical fine-tuning, often provide immediate answers rather than guiding students through the problem-solving process. This approach falls short of pedagogically…

Computation and Language · Computer Science 2024-10-08 Shashank Sonkar , Kangqi Ni , Sapana Chaudhary , Richard G. Baraniuk

Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work,…

Computation and Language · Computer Science 2024-06-21 Wenxuan Wang , Zhaopeng Tu , Chang Chen , Youliang Yuan , Jen-tse Huang , Wenxiang Jiao , Michael R. Lyu

Reinforcement learning from human feedback (RLHF) is a vital strategy for enhancing model capability in language models. However, annotating preference data for RLHF is a resource-intensive and creativity-demanding process, while existing…

Computation and Language · Computer Science 2024-04-02 Taiwei Shi , Kai Chen , Jieyu Zhao

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

Artificial Intelligence · Computer Science 2025-11-04 Mina Taraghi , Yann Pequignot , Amin Nikanjam , Mohamed Amine Merzouk , Foutse Khomh

Large language models (LLMs) are being integrated into socially assistive robots (SARs) and other conversational agents providing mental health and well-being support. These agents are often designed to sound empathic and supportive in…

Human-Computer Interaction · Computer Science 2026-02-05 Himanshi Lalwani , Hanan Salam

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

Computation and Language · Computer Science 2024-08-06 Yuxia Wang , Zenan Zhai , Haonan Li , Xudong Han , Lizhi Lin , Zhenxuan Zhang , Jingru Zhao , Preslav Nakov , Timothy Baldwin

Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models (LLMs). Traditionally, this method depends on selecting…

Computation and Language · Computer Science 2025-01-29 Xiaomin Li , Mingye Gao , Zhiwei Zhang , Jingxuan Fan , Weiyu Li

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of \textbf{course-correction}, \ie, the…

Computation and Language · Computer Science 2024-10-29 Rongwu Xu , Yishuo Cai , Zhenhong Zhou , Renjie Gu , Haiqin Weng , Yan Liu , Tianwei Zhang , Wei Xu , Han Qiu

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

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of…

Artificial Intelligence · Computer Science 2026-01-13 Tarun Raheja , Nilay Pochhi

Long-form question answering (LFQA) demands nuanced evaluation of multi-sentence explanatory responses, yet existing metrics often fail to reflect human judgment. We present LFQA-HP-1M, a large-scale dataset comprising 1.3M human pairwise…

Computation and Language · Computer Science 2026-03-02 Rafid Ishrak Jahan , Fahmid Shahriar Iqbal , Sagnik Ray Choudhury

Large language models (LLMs) now mediate many web-based mental-health, crisis, and other emotionally sensitive services, yet their psychosocial safety in these settings remains poorly understood and weakly evaluated. We present DialogGuard,…

Artificial Intelligence · Computer Science 2025-12-03 Han Luo , Guy Laban

ChatGLM is a free-to-use AI service powered by the ChatGLM family of large language models (LLMs). In this paper, we present the ChatGLM-RLHF pipeline -- a reinforcement learning from human feedback (RLHF) system -- designed to enhance…

Computation and Language · Computer Science 2024-04-04 Zhenyu Hou , Yilin Niu , Zhengxiao Du , Xiaohan Zhang , Xiao Liu , Aohan Zeng , Qinkai Zheng , Minlie Huang , Hongning Wang , Jie Tang , Yuxiao Dong

Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…

Computation and Language · Computer Science 2026-01-16 Vahideh Zolfaghari

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…

Computation and Language · Computer Science 2024-07-04 Wenhao Liu , Xiaohua Wang , Muling Wu , Tianlong Li , Changze Lv , Zixuan Ling , Jianhao Zhu , Cenyuan Zhang , Xiaoqing Zheng , Xuanjing Huang

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Computation and Language · Computer Science 2026-04-03 Simona-Vasilica Oprea , Adela Bâra

Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment.…

Computation and Language · Computer Science 2024-02-28 Feifan Song , Bowen Yu , Minghao Li , Haiyang Yu , Fei Huang , Yongbin Li , Houfeng Wang