LLM Safety Monitoring

LLM: Large Language Model

Follow this topic Ask about this topic

Latest papers

38 papers5 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

A Calibrated Instrument for Detecting Disposition Drift in Language Models
Oct 19, 2026Jerry KaplanLLM Safety Monitoring LLM Safety Evaluation
Adjunct Lecturer, Computer Science and Masters in International Policy, Stanford University
How Much Do Activation Monitors Benefit from Original Model Computations?
Oct 17, 2026James Oldfield, Shawn Im, Jay J Culligan +3LLM Safety Monitoring
University of Oxford · University of Wisconsin–Madison · Toyota Motor Europe
Reasoning Models Can Control Their Chains of Thought When They Tell Themselves To
Oct 16, 2026Uriel Dolev, Idan Schwartz, Yoav GoldbergLanguage Model Reasoning Evaluation LLM Prompting
Bar-Ilan University · Allen Institute for AI
TRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation
Oct 11, 2026Ankur Garg, Xuemin Yu, Hassan Sajjad +1LLM Safety LLM Safety Monitoring
University of Calgary · Dalhousie University · Mila - Quebec AI Institute
When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety
Sep 28, 2026Tianyi Guan, Jianhui Chen, Liangming PanLanguage Model Safety Evaluation LLM Interpretability
State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University
Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
Sep 27, 2026Gert Lek, Abele Malan, Chaoyi Zhu +3LLM Safety Benchmarks LLM Guardrails
University of Neuchâtel · Delft University of Technology · IBM Research +1
Local Sparsity Enables Unsupervised LLM Safety Detection
Sep 17, 2026Xin Chen, Gil Kur, Alexander Shevchenko +1Sparse Autoencoders LLM Safety Monitoring
ETH Zürich
Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
Sep 16, 2026Alizishaan Khatri, Chiquita Prabhu, Omkar NeogiSafety Filtering LLM Safety
Wrynx Inc. · Independent Researcher
ForeSight: Enhancing Risk Monitoring via Early Safety Signal Distillation
Sep 12, 2026Hanling Wang, Chenlong Wei, Ling Xu +6LLM Safety Monitoring LLM Safety
University of California, San Diego · Xi’an Jiaotong-Liverpool University · East China Normal University +2
Safety Monitors Mostly Catch What the Model Already Refuses
Sep 5, 2026Sripad KarneLanguage Model Safety Evaluation LLM Guardrails
Columbia University
Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator
Aug 27, 2026Varun Singh, Anuj Doshi, Makesh Narsimhan Sreedhar +2Multimodal Content Moderation LLM Guardrails
NVIDIA Santa Clara, CA
Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms
Aug 23, 2026Naymul Islam, Nusrat Jahan Lia, Shubhashis Roy Dipta +2LLM Safety Benchmarks Language Model Safety Evaluation
BanglaLLM · Institute of Information Technology, University of Dhaka · University of Maryland, Baltimore County +2
BanglaVeilGuard: Cross-Script Safety Benchmarking and Lightweight Guardrails for Bangla Large Language Models
Aug 22, 2026Md. Rakibul Hassan, Muhammad Iqbal HossainLLM Safety Monitoring LLM Safety
BRAC University Dhaka, Bangladesh
No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios
Aug 22, 2026Afshin Orojlooyjadid, Hitesh PatelLLM Safety Evaluation LLM Safety Benchmarks
Oracle AI
ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions
Aug 11, 2026Xinzhe Huang, Biwu Yao, Kedong Xiu +4LLM Guardrails Language Model Calibration
State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, China · University of Electronic Science and Technology of China, Chengdu, China +3
Social Pressure Breaks Majority Voting in LLM Safety Panels
Aug 5, 2026Yibo Hu, Jiaming QuNormative Conformity in Language Models Safety Filtering
Illinois Institute of Technology · Amazon
Online Safety Monitoring for LLMs
Jul 2, 2026Mona Schirmer, Metod Jazbec, Alexander Timans +3Language Model Safety Evaluation LLM Safety Monitoring
UvA Bosch-Delta Lab, University of Amsterdam · University of Wisconsin Madison · Johns Hopkins University
HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety
Jul 2, 2026Navaneeth Sangameswaran, Preetham S, Ashmiya LeninLLM Safety Benchmarks Language Model Safety Evaluation
Astroware AI, Delaware, USA · Karunya Institute of Technology and Sciences, Coimbatore, India
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
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
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
Jun 20, 2026Jiayi Li, Kun ZhanRefusal Behavior in Language Models LLM Guardrails
Lanzhou University
I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automotive Contexts
Jun 12, 2026Shaun Feakins, Ibrahim Habli, Kim Littler +1Language Model-Based Control Language Model Safety Evaluation
UKRI AI Centre for Doctoral Training in Safe Artificial Intelligence Systems (SAINTS), University of York, York, UK · Jaguar Land Rover, Coventry, UK
Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs
Jun 9, 2026Huizhen Shu, Xuying Li, Piao XueLLM Guardrails Safety Filtering
ModelOneAI · yunshanai
RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks
Jun 6, 2026Abid Aziz, Hafsa Binte KibriaAdversarial Attacks on LLMs LLM Security
Department of Electrical & Computer Engineering Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
Investigating and Alleviating Harm Amplification in LLM Interactions
Jun 1, 2026Ruohao Guo, Wei Xu, Alan RitterMLLM Safety Language Model Safety Evaluation
Georgia Institute of Technology
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Jun 1, 2026Jiaqi Yu, Xin Wang, Yixu Wang +4Language Model Safety Evaluation LLM Guardrails
1Fudan University · 2Shanghai AI Laboratory
$D^2$ -Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals
May 25, 2026Aoxi Liu, Yupeng Chen, James Oldfield +5Language Model Safety Evaluation LLM Safety Monitoring
Torr Vision Group, University of Oxford · The Chinese University of Hong Kong, Shenzhen
Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
May 20, 2026Dylan Feng, Pragya Srivastava, Anca Dragan +1Language Model Safety Evaluation LLM Guardrails
University of California, Berkeley, USA · 3Google DeepMind, India.
Exploring and Developing a Pre-Model Safeguard with Draft Models
May 19, 2026Hongyu Cai, Arjun Arunasalam, Yiming Liang +2LLM Guardrails Safety Filtering
Purdue University West Lafayette, Indiana, USA · Florida International University Miami, Florida, USA
AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue
May 13, 2026Jihyung Park, Saleh Afroogh, Junfeng JiaoLanguage Model Safety Evaluation LLM Guardrails
The University of Texas at Austin

Oct 19, 2026J/K move · Enter open · S save

A Calibrated Instrument for Detecting Disposition Drift in Language Models

Jerry Kaplan

Adjunct Lecturer, Computer Science and Masters in International Policy, Stanford University

LLM Safety Monitoring LLM Safety Evaluation

Open paper AskPDF arXiv

Before language models are released, they are tested for harmful traits such as willingness to carry out dangerous requests, deception, power seeking, and sycophancy. The safe behavior these tests certify may degrade as models are modified, by topical fine-tuning, new training data, or changes to settings such as the depth of their reasoning. Most work reports such drift as single summary rates scored by another AI model, without the error analysis needed to interpret them. We adapt a calibrated measurement methodology recently developed for assessing how inference optimizations affect the quality of model outputs. Applying it to several misalignment dimensions in two open-weight models, we first establish the instrument's precision, showing that shifts of a few percentage points can be reliably detected. We then induce drift deliberately by fine-tuning on correct and on subtly harmful medical and financial advice; harmful advice induces a far greater shift than correct advice. Most strikingly, a model that reasons before answering can conceal the shift almost entirely in its answers, even though a direct reading of its internal state shows that its disposition has moved. With reasoning switched off, the same model shifts steadily as the share of harmful advice in its training grows. These results demonstrate the importance of testing safety with reasoning turned both on and off.