English
Related papers

Related papers: Role-Conditioned Refusals: Evaluating Access Contr…

200 papers

Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and…

Computation and Language · Computer Science 2026-02-03 Faaiz Joad , Majd Hawasly , Sabri Boughorbel , Nadir Durrani , Husrev Taha Sencar

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

We study mechanisms that permit program components to express role constraints on clients, focusing on programmatic security mechanisms, which permit access controls to be expressed, in situ, as part of the code realizing basic…

Programming Languages · Computer Science 2015-07-01 Radha Jagadeesan , Alan Jeffrey , Corin Pitcher , James Riely

The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and…

Artificial Intelligence · Computer Science 2025-09-16 Aadil Gani Ganie

In enterprise settings, organizational data is segregated, siloed and carefully protected by elaborate access control frameworks. These access control structures can completely break down if an LLM fine-tuned on the siloed data serves…

Cryptography and Security · Computer Science 2025-10-06 Bargav Jayaraman , Virendra J. Marathe , Hamid Mozaffari , William F. Shen , Krishnaram Kenthapadi

Multimodal large language models (MLLMs) excel at multimodal perception and understanding, yet their tendency to generate hallucinated or inaccurate responses undermines their trustworthiness. Existing methods have largely overlooked the…

Computation and Language · Computer Science 2024-12-17 Yuhao Wang , Zhiyuan Zhu , Heyang Liu , Yusheng Liao , Hongcheng Liu , Yanfeng Wang , Yu Wang

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Computation and Language · Computer Science 2026-04-29 Nirmalendu Prakash , Yeo Wei Jie , Amir Abdullah , Ranjan Satapathy , Erik Cambria , Roy Ka Wei Lee

Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench,…

Software Engineering · Computer Science 2026-05-22 Lukas Weidener , Marko Brkić , Mihailo Jovanović , Emre Ulgac , Aakaash Meduri

Recent work on relationship-based access control has begun to show how it can be applied to general computing systems, as opposed to simply being employed for social networking applications. The use of relationships to determine…

Cryptography and Security · Computer Science 2015-09-22 Jason Crampton , James Sellwood

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we…

Artificial Intelligence · Computer Science 2026-03-17 Rishab Alagharu , Ishneet Sukhvinder Singh , Shaibi Shamsudeen , Zhen Wu , Ashwinee Panda

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Machine Learning · Computer Science 2025-08-28 Dylan Sam , Alexander Robey , Andy Zou , Matt Fredrikson , J. Zico Kolter

Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mathematical reasoning. However, their potential in multi-turn Text-to-SQL tasks remains…

Computation and Language · Computer Science 2026-05-06 Le Zhou , Feng Yao , Fengcai Qiao , Bo Xu , Fangyuan Wang , Boyan Xu

Role-Based Access Control (RBAC) is a popular authorization model used to manage data-access constraints in a wide range of systems. RBAC usually defines the static view on the access rights. However, to ensure dependability of a system, it…

Software Engineering · Computer Science 2018-05-16 Inna Vistbakka , Elena Troubitsyna

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…

Computation and Language · Computer Science 2026-02-26 Xinpeng Wang , Mingyang Wang , Yihong Liu , Hinrich Schütze , Barbara Plank

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 (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-driven approach that reimagines LLM safety by decoupling it from…

Machine Learning · Computer Science 2025-11-11 Zihui Wu , Haichang Gao , Jiacheng Luo , Zhaoxiang Liu

Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior. However, in cases related to safety, without precise instructions to human…

Artificial Intelligence · Computer Science 2024-11-05 Tong Mu , Alec Helyar , Johannes Heidecke , Joshua Achiam , Andrea Vallone , Ian Kivlichan , Molly Lin , Alex Beutel , John Schulman , Lilian Weng

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely \textit{one-size-fits-all}…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Jiaxi Yang , Shicheng Liu , Yuchen Yang , Dongwon Lee

Safety alignment in large language models (LLMs) induces over-refusals -- where LLMs decline benign requests due to aggressive safety filters. We analyze this phenomenon in retrieval-augmented generation (RAG), where both the query intent…

Computation and Language · Computer Science 2025-10-14 Utsav Maskey , Mark Dras , Usman Naseem