{"total":15,"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":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23,"area":"safety"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2506.12484","title":"Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization","created":"2025-06-14","cited_by_count":4,"area":"safety"},{"id":"2509.11816","title":"Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning","created":"2025-09-15","cited_by_count":3,"area":"safety"},{"id":"2510.05169","title":"From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs","created":"2025-10-05","cited_by_count":2,"area":"safety"},{"id":"2603.02436","title":"TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models","created":"2026-03-02","cited_by_count":2,"area":"safety"},{"id":"2605.06846","title":"Narrow Secret Loyalty Dodges Black-Box Audits","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2608.14577","title":"HarmProfile: Characterizing Harmful Distributions in Frontier LLMs","created":"2026-06-11","cited_by_count":1,"area":"safety"},{"id":"2609.19472","title":"Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models","created":"2026-09-16","cited_by_count":1,"area":"safety"},{"id":"2508.13246","title":"Involuntary Jailbreak: On Self-Prompting Attacks","created":"2025-08-18","cited_by_count":0,"area":"safety"},{"id":"2602.08877","title":"Stress-Testing Alignment Audits With Prompt-Level Strategic Deception","created":"2026-02-09","cited_by_count":0,"area":"safety"},{"id":"2602.12124","title":"Alignment Risks from Capability-Seeking RL Training","created":"2026-02-12","cited_by_count":0,"area":"safety"},{"id":"2606.08892","title":"Diffuse AI Control on Fuzzy Tasks","created":"2026-06-08","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"}],"next_cursor":null}