NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations▲5.4k3.00
[PDF]For Research Purpose Only - Jailbreaking Large Language Models with Jailbreaking Research▼13k2.00
[PDF]Safety and Reasoning Vulnerabilities in Self-Rewarding Test-Time Reinforcement Learning▼4.3k2.00
[PDF]ControlBench: Did the Approval Actually Happen? Process-Grounded Auditing of Human Control over LLM Agents▼4.3k2.00
[PDF]Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents▼5.8k2.33
[PDF]Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners▲3952.67
[PDF]GuardValue: Estimating One-Step Values and Policy Effects with Cloned Trajectory Prefixes▲3.0k2.33
[PDF]On the Framing Effect of AI Red-Teaming Instructions: Evidence from Prior Exercises and Controlled Simulations▼4.3k2.00
[PDF]From Clues to Sensitive Disclosure: Measuring Multi-Turn Privacy Risk and Preventing Privacy Leakage in LLMs▲6.1k2.00
Withdrawn or desk rejected (231)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00