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979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart.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 Is One Reading Enough? Decision-Relevant Ambiguity in Constrained Reinforcement Learning▲6.1k2.00
[PDF]Frozen Input-Harm Probes under Compression: Retained AUROC Does Not Mean Retained Refusal▼1.2k1.67
[PDF]Uncommitted Drafts Track Words, Not Knowledge: Evasion and Representation Monitoring in Diffusion LMs▼1361.33
[PDF]Stop Stealing, Stop Attacking: Countering Benchmark Hacking with Kernel-Enforced Contracts Outside the Agent's Reach▼4.3k2.00
[PDF]AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories▼5.9k2.50
[PDF]Are Your Agents Ready to Evolve? Assessing Evolution-Readiness in Agents Through Paired Safety and Utility Scoring▲3.0k2.33
[PDF]SelfShield: Unlocking LLMs' Self-Protective Capability Against Jailbreak Attacks via a Resilient Anchor Layer▼5.8k2.33
[PDF]The Safety Criticality Number: Cascade Stability and Intervention Thresholds for AI Agents▼5.8k2.33
[PDF]When Weight Fidelity Misleads: Concept-Erasure Safety Edits Under Diffusion-Model Quantization▼1.2k1.67
[PDF]Defending Multi-turn Attacks On Large Language Models Through Active Intention Verification▲9.2k2.67
[PDF]ReQOR: Operator-Discrepancy Subspace Repair for Quantization-Conditioned Backdoors in Large Language Models▲3952.67
[PDF]True Claims, False Answer: Spot-Check Debate Is Limited by What the Honest Side Claims▼1.2k3.00
[PDF]Scalable Hierarchical Transformers for Multi-Turn Jailbreak Detection in Long Conversations▼1.2k1.67
[PDF]Telltale Circuits? A Controlled Comparison of Text, Activation, and Attribution-Graph Monitors for Covert LLM-Agent Sabotage▼1.2k1.67
[PDF]Boundary Unlocking Value for Safe Bayesian Optimization under Monotone Safety Constraints▼1.2k1.67
[PDF]False Belief Dissemination, Persistence and Mitigation in Multi-Agent Social Networks Through the Lens of the Mandela Effect▲3952.67
[PDF]Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment▼4.3k2.00
Withdrawn or desk rejected (231)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