English
Related papers

Related papers: CARE: Decoding Time Safety Alignment via Rollback …

200 papers

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…

Computation and Language · Computer Science 2025-04-15 Shaoqing Zhang , Zhuosheng Zhang , Kehai Chen , Rongxiang Weng , Muyun Yang , Tiejun Zhao , Min Zhang

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

Computation and Language · Computer Science 2025-01-23 Melissa Kazemi Rad , Huy Nghiem , Andy Luo , Sahil Wadhwa , Mohammad Sorower , Stephen Rawls

Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with…

Machine Learning · Computer Science 2025-09-30 Xuekang Wang , Shengyu Zhu , Xueqi Cheng

Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our investigation shows that these safety mechanisms predominantly…

Cryptography and Security · Computer Science 2025-08-28 Chao Huang , Zefeng Zhang , Juewei Yue , Quangang Li , Chuang Zhang , Tingwen Liu

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

As software grows in complexity to accommodate diverse features and platforms, software bloating has emerged as a significant challenge, adversely affecting performance and security. However, existing approaches inadequately address the…

Software Engineering · Computer Science 2025-03-13 Bo Lin , Shangwen Wang , Yihao Qin , Liqian Chen , Xiaoguang Mao

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Computation and Language · Computer Science 2024-04-02 Yixu Wang , Yan Teng , Kexin Huang , Chengqi Lyu , Songyang Zhang , Wenwei Zhang , Xingjun Ma , Yu-Gang Jiang , Yu Qiao , Yingchun Wang

Assessing the reliability of Large Language Models (LLMs) by confidence elicitation is a prominent approach to AI safety in high-stakes applications, such as healthcare and finance. Existing methods either require expensive computational…

Computation and Language · Computer Science 2026-04-08 Zhaohan Zhang , Ziquan Liu , Ioannis Patras

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

Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However, this over-optimization often prioritizes compliance,…

Artificial Intelligence · Computer Science 2026-05-14 Seanie Lee , Sangwoo Park , Yumin Choi , Gyeongman Kim , Minki Kang , Jihun Yun , Dongmin Park , Jongho Park , Sung Ju Hwang

Pilot readback of Air Traffic Control (ATC) voice instructions is a primary safeguard against miscommunication in air transportation. However, readback anomalies remain implicated in approximately 80% of aviation incidents. This…

Machine Learning · Computer Science 2026-05-29 Qihan Deng , Minghua Zhang , Yang Yang , Zhenyu Gao

Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program…

Software Engineering · Computer Science 2026-02-09 Jiangping Huang , Wenguang Ye , Weisong Sun , Jian Zhang , Mingyue Zhang , Yang Liu

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Artificial Intelligence · Computer Science 2025-07-14 Zeyang Sha , Hanling Tian , Zhuoer Xu , Shiwen Cui , Changhua Meng , Weiqiang Wang

Diffusion Language Models (DLMs) provide a promising alternative to autoregressive language models by generating text through iterative denoising and bidirectional refinement. However, this iterative generation paradigm also introduces…

Computation and Language · Computer Science 2026-05-14 Yejin Lee , Yo-Sub Han

Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial prompts). We propose Concept Alignment and Concept Manipulation CALM, an inference-time method…

Machine Learning · Computer Science 2025-10-20 Ruben Belo , Marta Guimaraes , Claudia Soares

Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models preserve the geometric…

Machine Learning · Computer Science 2025-11-25 Thong Bach , Thanh Nguyen-Tang , Dung Nguyen , Thao Minh Le , Truyen Tran

Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concerns about the safety…

Cryptography and Security · Computer Science 2025-05-22 Taiye Chen , Zeming Wei , Ang Li , Yisen Wang

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Computation and Language · Computer Science 2025-04-15 Yutao Mou , Yuxiao Luo , Shikun Zhang , Wei Ye

As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance safety awareness by analyzing potential safety risks during…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Fenghua Weng , Chaochao Lu , Xia Hu , Wenqi Shao , Wenjie Wang
‹ Prev 1 3 4 5 6 7 10 Next ›