Refusals

Follow this topic Ask about this topic

Recent momentum

+0%

16 papers in the last 28 days · 0.3% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

3 new papers

A weekly snapshot of new work published in Refusals.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Refusals.

Period ending 2026-09-07

10 new papers

A weekly snapshot of new work published in Refusals.

129 papers

Latest in Refusals

Browse all topics →

Refusal Lives Downstream of Persona in Chat Models
Jun 24, 2026Viola Zhong, Qirui LiRefusals Persona
LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
Jun 23, 2026Anastasiia Kucherenko, François Brouchoud, Dimitri Percia David +1Legal Domain Refusals
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
Jun 23, 2026Cosimo Galeone, Anna Ettorre, Minsu Park +2Mechanistic Interpretability Model Activations
Can LLMs Reliably Self-Report Adversarial Prefills, and How?
Jun 22, 2026Quang Minh Nguyen, Uzair Ahmed, Taegyoon KimLanguage Model Evasion Attacks Introspection Adapters
Selective Time Series Forecasting via Metalearning
Jun 22, 2026Ricardo Inácio, Vitor Cerqueira, Marília Barandas +1Multivariate Forecasting Time Series
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
Jun 22, 2026Arthur Wuhrmann, Gaetan Stein, Daniel Brunner +1Large Language Model Performance Crime Domain
The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
Jun 21, 2026Shivam Ratnakar, Kartikeya VatsLarge Language Model Safety Refusals
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
Jun 21, 2026Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee +5Refusals Fragility
AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?
Jun 19, 2026Jiaxi Yang, Chaewan Chun, Jason Lucas +2Large Audio Language Models Large Language Model Safety
What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?
Jun 18, 2026Sihui Dai, Mann PatelLarge Language Model Safety Compliance
Semantic Flip: Synthetic OOD Generation for Robust Refusal in Embodied Question Answering and Spatial Localization
Jun 15, 2026Dongbin Na, Chanwoo Kim, Giyun Choi +1Refusals Flips
The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements
Jun 11, 2026Md Jafrin Hossain, Mohammad Arif Hossain, Weiqi Liu +1Large Language Model Safety Modular Agentic Framework
Quality Is Not a Safety Proxy Under Quantization
Jun 8, 2026Sahil KadadekarQuantization Safety Evaluation
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Jun 8, 2026Gianluca Barmina, Federico Torrielli, Sven Harms +7Refusals Large Language Model Safety
Steering Vectors are an Adversarial Attack Surface
Jun 4, 2026Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3Language Model Evasion Attacks Activation Steering
Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration
Jun 3, 2026Cristina Carleo, Pietro Liguori, Naghmeh Ivaki +1Vulnerable Code Vulnerability Detection & Repair
(Mis)generalization of Helpful-only Fine-tuning
Jun 3, 2026Mohammad Omar Khursheed, Baram Sosis, Fabien RogerHarmful Fine-Tuning Finetuning
Expert-Aware Refusal Steering
Jun 2, 2026Anna C. Marbut, Daniel R. Olson, Travis J. WheelerRefusals Mixture-Of-Expert Language Models
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
Jun 2, 2026Qinyan Zhou, Peixin Zhang, Jun Sun +2Large Language Model Safety Refusals
Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing
Jun 1, 2026Alexandre Cristovão MaioranoLarge Language Model Safety Refusals
A New Framework for Cybersecurity Refusals in AI Agents
May 31, 2026Eliot Krzysztof Jones, Mateusz Dziemian, Matt Fredrikson +1Cybersecurity Artificial Intelligence Safety
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
May 31, 2026Rashad Aziz, Ikhlasul Akmal Hanif, Fajri KotoMultilingual Safety Large Language Model Safety
BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
May 28, 2026Caleb DeLeeuwRefusals Large Language Model Safety
NumLeak: Public Numeric Benchmarks as Latent Labels in Foundation Models
May 28, 2026Anany KotawalaLeakage Foundation Model
Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures
May 28, 2026Junyoung Park, Sunghwan Park, Seongyong Ju +1Higher Attack Success Rates Large Language Model Safety
SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing
May 28, 2026Almene De Meran Meguimtsop, Maria Leonor Pacheco, Daniel E. AcunaAcademic Integrity Scientific Discovery
Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests
May 27, 2026Richard J. Young, Gregory D. MoodyCode Quality Large Language Model Safety
Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
May 27, 2026Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta +4Refusals Model Activations
A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving
May 26, 2026Sahil KadadekarLarge Language Model Safety Refusals
When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery
May 26, 2026Neel Tushar Shah, Manglam KartikArtificial Intelligence Scientists Verifier
ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
May 26, 2026Ruihao Pan, Suhang WangLarge Language Model Unlearning In-Context Learning
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
May 26, 2026Kia-Jüng Yang, Dominik Meier, Jiachen Zhao +2Refusals Large Reasoning Models
SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
May 25, 2026Khalid Yusuf DahirLarge Language Model Safety Low-Resource Languages
Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
May 22, 2026Qitao Tan, Xiaoying Song, Arman Akbari +7Safety Alignment Refusals
Latent-space Attacks for Refusal Evasion in Language Models
May 20, 2026Giorgio Piras, Raffaele Mura, Fabio Brau +4Refusals Large Language Model Safety
CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
May 20, 2026Heajun An, Qi Zhang, Vedanth Achanta +1Large Language Model Safety Guardrail
RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
May 20, 2026Lukas Weidener, Marko Brkić, Mihailo Jovanović +2Refusals Frontier Models
PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Negotiations
May 19, 2026Yingjie LeiNegotiation Agentic Commerce
Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
May 18, 2026Bryce Hinkley, Peyman NajafiradDiffusion Editing Refusals
Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
May 18, 2026Jiahe Guo, Xiangran Guo, Jiaxuan Chen +6Large Language Model Safety Multi-Modal Large Language Models
Auditing Discriminatory Patterns in Mortgage Lending Through Association Rules and Fair Binning
May 16, 2026Archit Rathod, Dhwani Chande, Het NagdaDisparities Data Mining
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
May 16, 2026Puning Yang, Junchi Yu, Qizhou Wang +3Large Language Model Unlearning Unlearning Aims
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
May 15, 2026Jiahui Guang, Haiyan Wang, Yingjie Zhu +4Large Language Model Unlearning Multi-Modal Large Language Models
Non-linear Interventions on Large Language Models
May 14, 2026Sangwoo KimSubspace Intervention Framework Refusals
Targeted Neuron Modulation via Contrastive Pair Search
May 12, 2026Sam Herring, Jake Naviasky, Karan MalhotraInstruction-Tuned Models Large Language Model Alignment
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
May 11, 2026Mengqi He, Xinyu Tian, Xin Shen +6Jailbreak Evaluations Jailbreak Detection
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
May 9, 2026Sangyeon Yoon, Wonje Jeung, Yoonjun Cho +2Benign Refusals
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
May 9, 2026Yu Chen, Yuanhao Liu, Qi CaoLarge Language Model Jailbreaks Jailbreak Attacks
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
May 7, 2026Zhe Liu, Zonghao Ying, Wenxin Zhang +5Large Language Model Safety Large Language Model Agents
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
May 7, 2026Qiyao Liang, Risto Miikkulainen, Ila FieteLarge Language Model Hallucination Hidden States
FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking
May 6, 2026Denys Katerenchuk, Pablo Duboue, Keelan Evanini +6Banking Refusals
The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models
May 6, 2026Alif Al Hasan, Sumon BiswasLarge Language Model Safety Refusals
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
May 3, 2026Sadia Asif, Mohammad Mohammadi AmiriLarge Language Model Safety Adversarial Evaluation
Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
May 2, 2026Xulin Hu, Che Wang, Wei Yang Bryan Lim +2Jailbreak Detection Refusals
Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
Apr 29, 2026Wenhao Lan, Shan Li, Xinhua Lai +4Refusals Large Language Model Safety
Delineating Knowledge Boundaries for Honest Large Vision-Language Models
Apr 29, 2026Junru Song, Yimeng Hu, Yijing Chen +4Large Vision Language Models Large Language Model Hallucination
Multilingual Refusal Alignment for Safer Large Language Models
Apr 24, 2026Aleksandra Krasnodębska, Wojciech Kusa, Aldo LipaniMultilingual Safety Cross-Lingual Alignment
Recognition Without Authorization: LLMs and the Moral Order of Online Advice
Apr 24, 2026Tom van NuenenMoral Reasoning Large Language Model Decision-Making
Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
Apr 20, 2026Wentao Zhang, Yan Zhuang, ZhuHang Zheng +3Retrieval-Augmented Generation Systems Denial-Of-Service Attacks
Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems
Apr 19, 2026Tianyi Huang, Samuel Xu, Jason Tansong Dang +2Agentic Systems Refusals

Jun 24, 2026 · cs.AIJ/K move · Enter open · S save

Refusal Lives Downstream of Persona in Chat Models

Viola Zhong, Qirui Li

Independent · Department of Mathematics Pohang University of Science and Technology

Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been studied as separate mechanisms. We show they interact: a compliant persona gates refusal. In Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct, we extract a compliant model-persona direction and a refusal direction and intervene on both. Compliant persona steering suppresses refusal -- in Llama, the refusal rate falls from 97% to 2%. Reintroducing the refusal direction partially restores refusal at late layers but not at early ones. Projecting out the persona direction in a late-layer window restores it to baseline; projecting out a random direction does not. Refusal is therefore gated at the late-layer expression stage, downstream of where it is computed. Treating refusal as a single isolated direction misses its dependence on persona.

Refusals Persona Downstream Reasoning

Open paper Ask about it PDF