LLM Safety

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 200% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 272

All topics

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
Jul 2, 2026Thomas WinningerLLM Interpretability LLM Safety
Télécom SudParis, Évry-Courcouronnes, France · ENS Paris-Saclay, Gif-sur-Yvette, France
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
Jul 2, 2026Mahmoud Abdelfattah, Hamid Nasiri, Peter GarraghanLLM Guardrails Safety Filtering
Lancaster University · Mindgard
Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing
Jul 2, 2026Joshua PenmanLLM Fine-Tuning Framing Effects in Language Models
Independent Researcher
HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment
Jul 1, 2026Shei Pern Chua, Hao Wu, Qianli Ma +1Adversarial Attacks on LLMs LLM Safety Alignment
Tsinghua University · Microsoft · Southeast University
Addressing Over-Refusal in LLMs with Competing Rewards
Jun 30, 2026Taeyoun Kim, Aviral KumarRL for Language Model Reasoning LLM Safety
Carnegie Mellon University · SynthLabs
Defending Against Harmful Supervision Hidden in Benign Samples
Jun 29, 2026Bang An, Yibo Yang, Dandan Guo +3Supervised Fine-Tuning Fine-Tuning
1King Abdullah University of Science and Technology · School of Artificial Intelligence, Jilin University
CAREBench: A Child-Safety Risk Benchmark for Language Models
Jun 29, 2026Kaavya Krishna-Kumar, Elaine Lau, Vaughn Robinson +6LLM Safety Benchmarks Language Model Safety Evaluation
Handshake AI · University of California, Los Angeles · McGill University
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
Jun 28, 2026Subhadip MitraAdversarial Attacks on LLMs LLM Safety
Independent Researcher
The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning
Jun 27, 2026Will Hawkins, Kaivalya Rawal, Jonathan Rystrøm +8LLM Safety Benchmarks Multilingual Language Model Evaluation
Oxford Internet Institute, University of Oxford · Hasso Plattner Institute, University of Potsdam · Chinese University of Hong Kong +2
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
Jun 26, 2026Changyue Li, Jiaming He, Youliang Yuan +4Supervised Fine-Tuning LLM Safety Alignment
The Chinese University of Hong Kong, Shenzhen · Ant Group · Lero the Research Ireland Centre for Software, University of Limerick
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
Jun 26, 2026Ting Ma, Xiufeng Huang, Benlei Cui +43LLM Safety Benchmarks LLM Safety Alignment
RAS: Measuring LLM Safety Through Refusal Alignment
Jun 24, 2026Chang-Chieh Huang, Yan-Lun Chen, Chia-Mu Yu +1LLM Safety Alignment LLM Safety
National Yang Ming Chiao Tung University · Hon Hai Research Institute
MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
Jun 24, 2026Congbo Ma, Hu Wang, Yichun Zhang +1LLM Guardrails LLM Safety
New York University Abu Dhabi · Khalifa University · New York University
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
Jun 24, 2026Abrar Alotaibi, Raed Mughus, Moataz AhmedMultilingual Language Model Evaluation LLM Evaluation
Information and Computer Science Department, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia. · College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, Dammam, 31441, Saudi Arabia. · SDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia.
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety
Jun 23, 2026Shikai Qiu, Xiaowen Xu, Benlei Cui +55VLM Robustness Multimodal Large Language Models
One Year Later...The Harms Persist, But So Do We!
Jun 22, 2026Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar +1Mental Health Adversarial Attacks on LLMs
Northeastern University Boston, MA, USA · Florida International University Miami, FL, USA
IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages
Jun 22, 2026Parth Bramhecha, Smit Deshmukh, Sairaj Bodhale +2Multilingual Language Models Language Model Safety Evaluation
L3Cube-Labs, Pune
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
Jun 21, 2026Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee +5LLM Interpretability LLM Fine-Tuning
Zoom Communications · Korea University · Yonsei University +1
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
Jun 20, 2026Jiayi Li, Kun ZhanLLM Guardrails Multimodal Large Language Models
Lanzhou University
AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?
Jun 19, 2026Jiaxi Yang, Chaewan Chun, Jason Lucas +2Audio-Language Model Evaluation LLM Safety
Penn State University
What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?
Jun 18, 2026Sihui Dai, Mann PatelAdversarial Attacks on LLMs In-Context Learning
CapitalOne
Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families
Jun 18, 2026Abdul Rafay SyedLLM Auditing Emergent Misalignment in Language Models
Department of Computer Science Universität des Saarlandes Saarbrücken, Germany
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
Jun 18, 2026Haotian Xu, Zeyang Zhang, Linbao Li +3Speculative Decoding LLM Inference Acceleration
Zhejiang University, Hangzhou, China · Harbin Institute of Technology, Shenzhen, China · Huawei
A Variational Framework for LLM Generator-Regulator Games
Jun 16, 2026Quanyan ZhuLLM Safety Text Generation
Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA.
RepSelect: Robust LLM Unlearning via Representation Selectivity
Jun 15, 2026Filip Sondej, Yushi Yang, Adam MahdiLLM Safety Representation Geometry in Language Models
Independent · University of Oxford
Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
Jun 15, 2026Tong Che, Rui WuReward Hacking LLM Safety
Rutgers University
Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models
Jun 15, 2026Ke Miao, Jiaxin Li, Hongliang Chen +2LLM Safety Alignment LLM Safety
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou HighTech Zone (Binjiang) Blockchain and Data Security Research Institute, China · Li Auto Inc. +2
GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking
Jun 14, 2026Aman Anifer, Vignesh Kumar Kembu, Vishnu M +4Adversarial Prompt Generation LLM Safety
Department of Computer Applications, Cochin University of Science and Technology, Kerala, India. · Department of Electrical, Computer and Biomedical Engineering, University of Pavia, A. Ferrata, 5, Pavia, 27100, Italy.
Constitutional Value Potentials: reading and steering internal priority margins in language models
Jun 13, 2026Tong Che, Rui WuLanguage Model Safety Evaluation LLM Safety
Rutgers University
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
Jun 13, 2026Wenbo Yu, Bohua Wang, Hao Fang +10LLM Safety Benchmarks Language Model Safety Evaluation
Tsinghua University · Beijing Normal University · South China University of Technology +2

Jul 2, 2026, cs.AIJ/K move · Enter open · S save

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP

Thomas Winninger

Télécom SudParis, Évry-Courcouronnes, France · ENS Paris-Saclay, Gif-sur-Yvette, France

LLM Interpretability LLM Safety Refusal Behavior in Language Models

Open paper AskPDF arXiv

Steering and monitoring activations in Large Language Models (LLMs) are increasingly used for both safety and interpretability. Early work assumed behaviours are encoded along single linear directions, but recent findings suggest complex behaviours, such as the refusal to answer harmful queries, live in multi-dimensional subspaces. However, existing methods for extracting these subspaces are computationally expensive, which becomes prohibitive on reasoning models who produce long reasoning traces. By adapting the Recursive Feature Machine (RFM) algorithm -- which can be computed efficiently -- with a probe-informed initialization, we are able to identify the multi-dimensional refusal subspace in seconds, on reasoning (Qwen 3) and non-reasoning (Qwen 2.5) models. While RFM allows for faster subspace identification, it also showed better performances on the ablation task than its alternatives. More work is planned to better understand the relations between subspaces found by different methods. If confirmed, RFM could be a cheap and scalable complement to existing subspace-extraction methods in LLMs.

Momentum

Related topics

Latest papers 272