{"total":17,"rows":[{"id":"2510.27062","title":"Consistency Training Helps Stop Sycophancy and Jailbreaks","created":"2025-10-31","cited_by_count":16,"area":"safety"},{"id":"2601.23081","title":"Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures","created":"2026-01-30","cited_by_count":5,"area":"safety"},{"id":"2509.25843","title":"ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack","created":"2025-09-30","cited_by_count":1,"area":"safety"},{"id":"2605.08765","title":"Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning","created":"2026-05-09","cited_by_count":1,"area":"safety"},{"id":"2606.23700","title":"Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment","created":"2026-06-04","cited_by_count":1,"area":"safety"},{"id":"2508.21448","title":"When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth","created":"2025-08-29","cited_by_count":0,"area":"safety"},{"id":"2605.20286","title":"Adaptive Probe-based Steering for Robust LLM Jailbreaking","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2606.17168","title":"RepSelect: Robust LLM Unlearning via Representation Selectivity","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2606.21147","title":"AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?","created":"2026-06-19","cited_by_count":0,"area":"safety"},{"id":"2608.08212","title":"Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment","created":"2026-08-08","cited_by_count":0,"area":"safety"},{"id":"2609.31062","title":"CG-Probes: Recovering Guardrail Directions from Patient Query Embeddings","created":"2026-09-25","cited_by_count":0,"area":"safety"},{"id":"2609.35356","title":"Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits","created":"2026-09-28","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":"2609.36657","title":"Constitutional adapters: Inference-time interventions for misalignment and misuse","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.39882","title":"LLM Persona Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.04245","title":"On the Steering Dimensionality of Refusal in Language Models","created":"2026-10-03","cited_by_count":0,"area":"safety"},{"id":"2610.17880","title":"Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}