- Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek V. Datla, Anoop Kumar, Zihan Guan, Sheng Li · Feb 24, 2026 · Citations: 0
Pairwise PreferenceRed Team Automatic Metrics
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs).
- SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing
Yifei Xu, Guilherme Potje, Shivam Shandilya, Tiancheng Yuan, Leonardo de Oliveira Nunes · Feb 24, 2026 · Citations: 0
Rubric RatingRed Team Automatic Metrics
Designing aligned and robust rewards for open-ended generation remains a key barrier to RL post-training.
- Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming
Ian Steenstra, Paola Pedrelli, Weiyan Shi, Stacy Marsella, Timothy W. Bickmore · Feb 23, 2026 · Citations: 0
Red Team Simulation Env
Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue.
- MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav, Ava Cai, Kevin Zhu · Feb 21, 2026 · Citations: 0
Red Team Automatic Metrics
Defending LLMs against adversarial jailbreak attacks remains an open challenge.
- FENCE: A Financial and Multimodal Jailbreak Detection Dataset
Mirae Kim, Seonghun Jeong, Youngjun Kwak · Feb 20, 2026 · Citations: 0
Red Team Automatic Metrics
A baseline detector trained on FENCE achieves 99 percent in-distribution accuracy and maintains strong performance on external benchmarks, underscoring the dataset's robustness for training reliable detection models.
- IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages
Priyaranjan Pattnayak, Sanchari Chowdhuri · Feb 18, 2026 · Citations: 0
Red Team Automatic Metrics
Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied.
- Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut · Feb 18, 2026 · Citations: 0
Red Team Automatic Metrics
LLM-based agents execute real-world workflows via tools and memory.
- Intent Laundering: AI Safety Datasets Are Not What They Seem
Shahriar Golchin, Marc Wetter · Feb 17, 2026 · Citations: 0
Red Team Automatic Metrics
We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice.
- Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Lukas Struppek, Adam Gleave, Kellin Pelrine · Feb 16, 2026 · Citations: 0
Red Team Automatic Metrics
As the capabilities of large language models continue to advance, so does their potential for misuse.
- Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis · Feb 12, 2026 · Citations: 0
Red Team Automatic Metrics
Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems.
- What Matters For Safety Alignment?
Xing Li, Hui-Ling Zhen, Lihao Yin, Xianzhi Yu, Zhenhua Dong · Jan 7, 2026 · Citations: 0
Red Team Automatic Metrics Tool Use
This paper presents a comprehensive empirical study on the safety alignment capabilities.
- Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Iker García-Ferrero, David Montero, Roman Orus · Dec 18, 2025 · Citations: 0
Red Team Automatic Metrics
We replace fragile pattern-based refusal detection with an LLM-as-a-judge that assigns refusal confidence scores and we propose a ridge-regularized variant to compute steering vectors that better isolate the refusal--compliance direction.
- Reasoning Up the Instruction Ladder for Controllable Language Models
Zishuo Zheng, Vidhisha Balachandran, Chan Young Park, Faeze Brahman, Sachin Kumar · Oct 30, 2025 · Citations: 0
Red Team Automatic Metrics
Our finetuned models achieve consistent improvements on instruction following and instruction hierarchy benchmarks, achieving roughly a 20% improvement on the IHEval conflict setup.
- A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
Xuan Luo, Yue Wang, Zefeng He, Geng Tu, Jing Li · Sep 17, 2025 · Citations: 0
Red Team Automatic Metrics
This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses.
- Role-Aware Language Models for Secure and Contextualized Access Control in Organizations
Saeed Almheiri, Yerulan Kongrat, Adrian Santosh, Ruslan Tasmukhanov, Josemaria Loza Vera · Jul 31, 2025 · Citations: 0
Red Team Automatic Metrics
Existing safety methods typically assume uniform access and focus on preventing harmful or toxic outputs, without addressing role-specific access constraints.
- When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
Yuxin Xiao, Sana Tonekaboni, Walter Gerych, Vinith Suriyakumar, Marzyeh Ghassemi · Jun 9, 2025 · Citations: 0
Red Team Automatic Metrics
In this work, we seek to understand whether style patterns compromise LLM safety, how superficial style alignment increases model vulnerability, and how best to mitigate these risks during alignment.
- RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Zeyi Liao, Jaylen Jones, Linxi Jiang, Yuting Ning, Eric Fosler-Lussier · May 28, 2025 · Citations: 0
Red Team Simulation Env Web Browsing
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection.
- Refusal Direction is Universal Across Safety-Aligned Languages
Xinpeng Wang, Mingyang Wang, Yihong Liu, Hinrich Schütze, Barbara Plank · May 22, 2025 · Citations: 0
Red Team Automatic Metrics
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety.
- Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
Yubo Li, Xiaobin Shen, Xinyu Yao, Xueying Ding, Yidi Miao · Apr 7, 2025 · Citations: 0
Red Team Automatic Metrics
We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies (in-cont
- Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Hanjiang Hu, Alexander Robey, Changliu Liu · Feb 28, 2025 · Citations: 0
Red Team Automatic Metrics
To address this challenge, we propose a safety steering framework grounded in safe control theory, ensuring invariant safety in multi-turn dialogues.
