English
Related papers

Related papers: Refusal Falls off a Cliff: How Safety Alignment Fa…

200 papers

Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to…

Artificial Intelligence · Computer Science 2026-04-17 Yi Zhao , Yajuan Peng , Cam-Tu Nguyen , Zuchao Li , Xiaoliang Wang , Xiaoming Fu , Hai Zhao

Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help evading rules imposed by an illegitimate authority, rules that are deeply unjust or absurd…

Artificial Intelligence · Computer Science 2026-04-09 Cameron Pattison , Lorenzo Manuali , Seth Lazar

Refusal-Aware Instruction Tuning (RAIT) enables Large Language Models (LLMs) to refuse to answer unknown questions. By modifying responses of unknown questions in the training data to refusal responses such as "I don't know", RAIT enhances…

Computation and Language · Computer Science 2024-12-23 Runchuan Zhu , Zhipeng Ma , Jiang Wu , Junyuan Gao , Jiaqi Wang , Dahua Lin , Conghui He

Training safe LLMs remains a critical challenge. The most widely used method, Refusal Training (RT), struggles to generalize against various Out-of-Distribution (OOD) jailbreaking attacks. Although various advanced methods have been…

Machine Learning · Computer Science 2025-06-02 Haoyu Wang , Zeyu Qin , Li Shen , Xueqian Wang , Dacheng Tao , Minhao Cheng

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…

Computation and Language · Computer Science 2025-12-22 Riad Ahmed Anonto , Md Labid Al Nahiyan , Md Tanvir Hassan

Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability, while existing metrics fail to capture this ability. In this…

Computation and Language · Computer Science 2026-05-19 Wenbo Pan , Jie Xu , Qiguang Chen , Junhao Dong , Libo Qin , Xinfeng Li , Haining Yu , Xiaohua Jia

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving…

Computation and Language · Computer Science 2026-02-05 Zhaotian Weng , Haoxuan Li , Xin Eric Wang , Kuan-Hao Huang , Jieyu Zhao

Large Language Models (LLMs) exhibit impressive reasoning abilities, yet their reliance on structured step-by-step processing reveals a critical limitation. In contrast, human cognition fluidly adapts between intuitive, heuristic (System 1)…

Computation and Language · Computer Science 2025-10-16 Alireza S. Ziabari , Nona Ghazizadeh , Zhivar Sourati , Farzan Karimi-Malekabadi , Payam Piray , Morteza Dehghani

Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reasoning should lead to more robust safety behavior, we find evidence to the contrary:…

Artificial Intelligence · Computer Science 2026-05-26 Jianli Zhao , Tingchen Fu , Rylan Schaeffer , Mrinank Sharma , Fazl Barez

While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and…

Cryptography and Security · Computer Science 2026-02-17 Yanbo Wang , Minzheng Wang , Jian Liang , Lu Wang , Yongcan Yu , Ran He

Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal…

Artificial Intelligence · Computer Science 2026-04-17 Rikard Rosenbacke , Carl Rosenbacke , Victor Rosenbacke , Martin McKee

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

Computation and Language · Computer Science 2025-05-27 Xiaochen Zhu , Caiqi Zhang , Tom Stafford , Nigel Collier , Andreas Vlachos

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Renmiao Chen , Yida Lu , Shiyao Cui , Xuan Ouyang , Victor Shea-Jay Huang , Shumin Zhang , Chengwei Pan , Han Qiu , Minlie Huang

How do multi-turn reasoning systems fail? The expected answer is logical contradiction, in which the system's maintained state becomes unsatisfiable. We show that the dominant mode is instead satisfiable drift, where the internal state…

Artificial Intelligence · Computer Science 2026-05-26 Sebastien Kawada

Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets, where unsafe prompts are paired with standard refusal templates, often leads to false…

Machine Learning · Computer Science 2026-03-17 Quan Liu , Han Zhou , Wenquan Wu , Hua Wu , Sen Su

Large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, enabling them to answer a wide range of questions across various domains. However, these models are not flawless and often produce…

Computation and Language · Computer Science 2024-09-23 Lang Cao

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

Artificial Intelligence · Computer Science 2026-05-12 Xiangkun Sun , Lingkai Kong , Aoqi Zhang , Liang Zeng , Tonghan Wang

The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large language models~(LLMs). However, their enhanced capabilities,…

Computers and Society · Computer Science 2025-11-18 Kaiwen Zhou , Chengzhi Liu , Xuandong Zhao , Shreedhar Jangam , Jayanth Srinivasa , Gaowen Liu , Dawn Song , Xin Eric Wang

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.…

Cryptography and Security · Computer Science 2026-05-19 Tim Beyer , Sophie Xhonneux , Simon Geisler , Gauthier Gidel , Leo Schwinn , Stephan Günnemann
‹ Prev 1 8 9 10 Next ›