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979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart.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]Measuring Say-Do Consistency in Tool-Using Agents: A Claim-Execution Traceability Framework▼1.2k1.67
[PDF]The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning▼1.2k1.67
[PDF]Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning▼1361.33
[PDF]Certify, Then Act: Formal Safety Certificates for Cooperative LLM Agents in Stochastic Environments▲3952.67
[PDF]One Calibration, Many Requests: Amortized Black-Box Multimodal Jailbreaking via Cross-Model Refusal Coordinates▲14k3.00
[PDF]LatentCompass: T2I Diffusion Steering via Orthogonal Attribute Spaces for Debiasing, Concept Erasure, and Red Teaming▲14k3.00
[PDF]Safe in Text, Unsafe in Action: Distinguishing Content and Physical Danger in LLM Hidden States▼4.5k2.67
[PDF]Moderating Covertly Sensitive Images Across Policies: Policy-Reconfigurable Benchmark and Zero-Shot Method▼1.2k1.67
[PDF]Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning▲3952.67
[PDF]EvoSteer: Restoring Safety in Experience-Driven Agentic Evolution via Activation Steering▲2.0k4.00
[PDF]Authorization Closure Graph: Minimal Repair for LLM Agents with Evolving User Instructions▼14k2.00
[PDF]AmbiguityBench: Reasoning Modes Bidirectionally Shift Ambiguity Sensitivity in Frontier LLMs▼1.2k1.67
[PDF]SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation▲9.2k2.67
[PDF]Empathetic yet Guarded: Dynamic Personalized Safety Alignment in Multi-Turn Conversations▲3.0k2.33
[PDF]Offline Scores Overestimate Online Oversight: Timely Interception of LLM Agents with Causal-Cone Monitoring▼4.3k2.00
[PDF]Target-Coherent Risk Envelopes: Sharp Completion Bounds for Overlapping Forecast Adaptation▼1.2k1.67
Withdrawn or desk rejected (231)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