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979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart.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]CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents▼4.3k2.00
[PDF]Beyond the Transcript: Detecting Covert Coordination in Latent Multi-Agent Communication▼4.3k2.00
[PDF]The Irreversibility Threshold: When Error in LLM Agent Pipelines Outruns Human Correction▼1361.33
[PDF]The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology▼4.3k2.00
[PDF]Beyond Jailbreak Rates: Harm Centric Evaluation of Multi Turn Jailbreak Attacks and Defenses▼4.3k2.00
[PDF]When Can Old Evaluations Certify a New Model? Matching Label-Complexity Bounds Under Evaluator-Residual Drift▼4.5k2.67
[PDF]SafeDrift: Reliability-Audited Longitudinal Safety Evaluation of Memory-Augmented Mental-Health Agents▲6.1k2.00
[PDF]Conditional Backdoors Leave Traces in J-Space of Code-Generating Large Language Models▼1.2k1.67
[PDF]Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes▼1.2k1.67
[PDF]How Jailbreak Attacks Inform LLM Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions▼5.8k2.33
Withdrawn or desk rejected (231)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