English
Related papers

Related papers: Superficial Safety Alignment Hypothesis

200 papers

Large language models (LLMs) have become an important semantic infrastructure for modern recommender systems. A prevailing paradigm integrates LLM-derived semantic embeddings with collaborative representations via representation alignment,…

Information Retrieval · Computer Science 2026-04-27 Maolin Wang , Dongze Wu , Jianing Zhou , Hongyu Chen , Beining Bao , Yu Jiang , Chenbin Zhang , Chang Wang , Jian Liu , Lei Sha

While static analysis is useful in detecting early-stage hardware security bugs, its efficacy is limited because it requires information to form checks and is often unable to explain the security impact of a detected vulnerability. Large…

Cryptography and Security · Computer Science 2025-05-01 Baleegh Ahmad , Hammond Pearce , Ramesh Karri , Benjamin Tan

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Large language models (LLMs) can be prompted with specific styles (e.g., formatting responses as lists), including in malicious queries. Prior jailbreak research mainly augments these queries with additional string transformations to…

Machine Learning · Computer Science 2026-02-26 Yuxin Xiao , Sana Tonekaboni , Walter Gerych , Vinith Suriyakumar , Marzyeh Ghassemi

Recent advances in Large Vision-Language Models (LVLMs) have showcased strong reasoning abilities across multiple modalities, achieving significant breakthroughs in various real-world applications. Despite this great success, the safety…

Computation and Language · Computer Science 2024-12-02 Chenhang Cui , Gelei Deng , An Zhang , Jingnan Zheng , Yicong Li , Lianli Gao , Tianwei Zhang , Tat-Seng Chua

Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to…

Computation and Language · Computer Science 2025-05-27 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

The emergence of large language models (LLMs) has sparked the possibility of about Artificial Superintelligence (ASI), a hypothetical AI system surpassing human intelligence. However, existing alignment paradigms struggle to guide such…

Machine Learning · Computer Science 2024-12-30 HyunJin Kim , Xiaoyuan Yi , Jing Yao , Jianxun Lian , Muhua Huang , Shitong Duan , JinYeong Bak , Xing Xie

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Cryptography and Security · Computer Science 2025-09-19 Yuanbo Xie , Yingjie Zhang , Tianyun Liu , Duohe Ma , Tingwen Liu

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…

Computation and Language · Computer Science 2024-06-07 Javier Rando , Francesco Croce , Kryštof Mitka , Stepan Shabalin , Maksym Andriushchenko , Nicolas Flammarion , Florian Tramèr

Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail…

Machine Learning · Computer Science 2025-09-16 Peixuan Han , Cheng Qian , Xiusi Chen , Yuji Zhang , Heng Ji , Denghui Zhang

Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar…

Computation and Language · Computer Science 2025-08-11 Sayantan Adak , Pratyush Chatterjee , Somnath Banerjee , Rima Hazra , Somak Aditya , Animesh Mukherjee

As robots acquire increasingly sophisticated skills and see increasingly complex and varied environments, the threat of an edge case or anomalous failure is ever present. For example, Tesla cars have seen interesting failure modes ranging…

Robotics · Computer Science 2023-09-13 Amine Elhafsi , Rohan Sinha , Christopher Agia , Edward Schmerling , Issa Nesnas , Marco Pavone

Alignment training is crucial for enabling large language models (LLMs) to cater to human intentions and preferences. It is typically performed based on two stages with different objectives: instruction-following alignment and…

Computation and Language · Computer Science 2024-06-24 Chenglong Wang , Hang Zhou , Kaiyan Chang , Bei Li , Yongyu Mu , Tong Xiao , Tongran Liu , Jingbo Zhu

Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficiently addressed by techniques developed for dense models. In…

Machine Learning · Computer Science 2025-10-14 Zhenglin Lai , Mengyao Liao , Bingzhe Wu , Dong Xu , Zebin Zhao , Zhihang Yuan , Chao Fan , Jianqiang Li

The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt to mitigate this via data selection, they typically rely on…

Machine Learning · Computer Science 2026-01-13 Haozhong Wang , Zhuo Li , Yibo Yang , He Zhao , Hongyuan Zha , Dandan Guo

Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Xianhui Zhang , Chengyu Xie , Linxia Zhu , Yonghui Yang , Weixiang Zhao , Zifeng Cheng , Cong Wang , Fei Shen , Tat-Seng Chua

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Computation and Language · Computer Science 2026-02-03 Yuxuan Lu , Yongkang Guo , Yuqing Kong

Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration? Our study, focusing on safety-sensitive…

Computation and Language · Computer Science 2024-06-10 Yu Fu , Yufei Li , Wen Xiao , Cong Liu , Yue Dong

As Large Language Models are rapidly deployed across diverse applications from healthcare to financial advice, safety evaluation struggles to keep pace. Current benchmarks focus on single-turn interactions with generic policies, failing to…

Cryptography and Security · Computer Science 2025-10-28 Madhur Jindal , Hari Shrawgi , Parag Agrawal , Sandipan Dandapat

Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods…

Cryptography and Security · Computer Science 2026-04-21 Bo Yan , Weikai Lin , Yada Zhu , Song Wang
‹ Prev 1 8 9 10 Next ›