{"total":29,"rows":[{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2510.27062","title":"Consistency Training Helps Stop Sycophancy and Jailbreaks","created":"2025-10-31","cited_by_count":16,"area":"safety"},{"id":"2407.20181","title":"Blockchain for Large Language Model Security and Safety: A Holistic Survey","created":"2024-07-26","cited_by_count":8,"area":"safety"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2409.01247","title":"Conversational Complexity for Assessing Risk in Large Language Models","created":"2024-09-02","cited_by_count":6,"area":"safety"},{"id":"2603.26142","title":"Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models","created":"2026-03-27","cited_by_count":3,"area":"safety"},{"id":"2506.05376","title":"A Red Teaming Roadmap Towards System-Level Safety","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2508.10033","title":"Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7","created":"2025-08-09","cited_by_count":2,"area":"safety"},{"id":"2508.16325","title":"ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2605.21834","title":"On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation","created":"2026-05-20","cited_by_count":2,"area":"safety"},{"id":"2605.13334","title":"LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs","created":"2026-05-13","cited_by_count":1,"area":"safety"},{"id":"2606.00975","title":"Lost in Delusion: Examining LLM Safety Under User Delusions and Distress","created":"2026-05-31","cited_by_count":1,"area":"safety"},{"id":"2512.03047","title":"Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models","created":"2025-11-19","cited_by_count":0,"area":"safety"},{"id":"2604.24700","title":"Green Shielding: A User-Centric Approach Towards Trustworthy AI","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2605.06213","title":"Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2606.23884","title":"One Year Later...The Harms Persist, But So Do We!","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"id":"2606.24267","title":"Pigeonholing: how bad prompts hurt models, causing collapse and mistakes","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.09804","title":"Trivial Prompt Reframing Bypasses Safety Guardrails in Google\\'s MedGemma-4B","created":"2026-07-09","cited_by_count":0,"area":"safety"},{"id":"2609.03247","title":"Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models","created":"2026-09-03","cited_by_count":0,"area":"safety"},{"id":"2609.20129","title":"Local Sparsity Enables Unsupervised LLM Safety Detection","created":"2026-09-17","cited_by_count":0,"area":"safety"},{"id":"2609.35544","title":"Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2609.38357","title":"Evaluating Language Model Safety Across Long Adversarial Conversations","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.38909","title":"Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2609.39882","title":"LLM Persona Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.06064","title":"TrustMI: Causally controlling how assistants trust their users","created":"2026-10-05","cited_by_count":0,"area":"safety"},{"id":"2610.08540","title":"Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements","created":"2026-10-06","cited_by_count":0,"area":"safety"},{"id":"2610.08840","title":"Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}