English
Related papers

Related papers: Superficial Safety Alignment Hypothesis

200 papers

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…

With the growing prevalence of large language models (LLMs), the safety of LLMs has raised significant concerns. However, there is still a lack of definitive standards for evaluating their safety due to the subjective nature of current…

Computation and Language · Computer Science 2025-06-10 Chuxue Cao , Han Zhu , Jiaming Ji , Qichao Sun , Zhenghao Zhu , Yinyu Wu , Juntao Dai , Yaodong Yang , Sirui Han , Yike Guo

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe…

Artificial Intelligence · Computer Science 2026-02-18 Ankit Sharma , Nachiket Tapas , Jyotiprakash Patra

As large language models (LLMs) continue to advance in capabilities, ensuring their safety against jailbreak attacks remains a critical challenge. In this paper, we introduce a novel safety alignment approach called Answer-Then-Check, which…

Machine Learning · Computer Science 2026-03-09 Chentao Cao , Xiaojun Xu , Bo Han , Hang Li

Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased…

Robotics · Computer Science 2024-06-11 Xiangrui Kong , Thomas Braunl , Marco Fahmi , Yue Wang

In UAV dynamic decision, complex and variable hazardous factors pose severe challenges to the generalization capability of algorithms. Despite offering semantic understanding and scene generalization, Large Language Models (LLM) lack…

Robotics · Computer Science 2026-03-02 Wenzhe Zhao , Yang Zhao , Ganchao Liu , Zhiyu Jiang , Dandan Ma , Zihao Li , Xuelong Li

Reasoning-capable LLMs have achieved major breakthroughs in solving complex problems, but recent work shows that acquiring and deploying strong reasoning can introduce significant safety risks. A common mitigation is to apply a secondary…

Artificial Intelligence · Computer Science 2026-02-03 Yihao Xue , Baharan Mirzasoleiman

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…

Artificial Intelligence · Computer Science 2025-10-27 Jingnan Zheng , Xiangtian Ji , Yijun Lu , Chenhang Cui , Weixiang Zhao , Gelei Deng , Zhenkai Liang , An Zhang , Tat-Seng Chua

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

As Artificial General Intelligence (AGI) becomes increasingly integrated into various facets of human life, ensuring the safety and ethical alignment of such systems is paramount. Previous studies primarily focus on single-modality threats,…

Artificial Intelligence · Computer Science 2025-02-18 Siyin Wang , Xingsong Ye , Qinyuan Cheng , Junwen Duan , Shimin Li , Jinlan Fu , Xipeng Qiu , Xuanjing Huang

Subjective Answer Grading (SAG) plays a crucial role in education, standardized testing, and automated assessment systems, particularly for evaluating short-form responses in Short Answer Scoring (SAS). However, existing approaches often…

Computation and Language · Computer Science 2025-05-16 Peichao Lai , Kexuan Zhang , Yi Lin , Linyihan Zhang , Feiyang Ye , Jinhao Yan , Yanwei Xu , Conghui He , Yilei Wang , Wentao Zhang , Bin Cui

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Machine Learning · Computer Science 2025-05-01 Yi Zhou , Wenpeng Xing , Dezhang Kong , Changting Lin , Meng Han

Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities. Existing mitigation strategies typically rely on global…

Machine Learning · Computer Science 2026-01-09 Wang Cai , Yilin Wen , Jinchang Hou , Du Su , Guoqiu Wang , Zhonghou Lv , Chenfu Bao , Yunfang Wu

We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical question arises here:…

Computation and Language · Computer Science 2024-12-24 Minlie Huang , Yingkang Wang , Shiyao Cui , Pei Ke , Jie Tang

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…

Machine Learning · Computer Science 2024-12-06 Jason Vega , Junsheng Huang , Gaokai Zhang , Hangoo Kang , Minjia Zhang , Gagandeep Singh

Reliable collision avoidance under extreme situations remains a critical challenge for autonomous vehicles. While large language models (LLMs) offer promising reasoning capabilities, their application in safety-critical evasive maneuvers is…

Robotics · Computer Science 2025-06-12 Shiyue Zhao , Junzhi Zhang , Neda Masoud , Heye Huang , Xiaohui Hou , Chengkun He

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

Artificial Intelligence · Computer Science 2026-05-12 Yi Zhang , Yuxin Chen , Leheng Sheng , Dongcheng Zhang , Chaochao Lu , Xiang Wang , An Zhang

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.…

Software Engineering · Computer Science 2026-02-26 Kangning Shen , Jingyuan Zhang , Chenxi Sun , Wencong Zeng , Yang Yue

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

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Machine Learning · Computer Science 2026-01-14 Minglai Yang , Xinyu Guo , Zhengliang Shi , Jinhe Bi , Steven Bethard , Mihai Surdeanu , Liangming Pan