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
362 results for “keyword:"ai safety"” in ICLR 2027. 80 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Disentangling Verbalized Evaluation Awareness and Refusal through Neuron-Level Intervention▼4.3k2.00
[PDF]Action-Conditioned Predictive Consistency for Adversarial Detection in Vision-Language-Action Models▼4.3k2.00
[PDF]Before You Report a Null: A Two-Sided Pre-Flight Screen for Shutdown-Resistance Evaluations▲11.00
[PDF]PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction▲6.1k2.00
[PDF]A Jailbreak Success Coordinate Outside the Refusal Subspace: Decodable Before Generation, Reachable from the Input▼5.8k2.33
[PDF]The Signal Survives, the Threshold Slips: Small LLM Agents After Quantization and Fine-Tuning▼1.2k1.67
[PDF]Runtime Monitoring of Distributed Backdoors in Multi-Agent LLM Systems: Local Detection, Encoding Changes, and Blocking▼5.9k2.50
[PDF]Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?▲11k2.00
[PDF]The Verbalization Gap: Stress-Testing Activation Monitoring with Natural Language Autoencoders▼1361.33
[PDF]Admission Control for Multi-Agent LLM Systems: Enforcing Safety Invariants on the Connection Graph▲6.1k2.00
[PDF]From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models▼1361.33
[PDF]Placebo Audits Quantify Audit-Specific Acceptance under Adaptive Reuse of Verifier Tests▼5.8k2.33
[PDF]Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception▼1.1k3.25
[PDF]Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models▼4.3k2.00
[PDF]Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization▼4.5k2.67
Withdrawn or desk rejected (80)
[PDF]Shared Parametric Geometry and Data Provenance in Model Organisms for Emergent MisalignmentWithdrawn2.00
[PDF]Teaching Language Models to Say What They Know: Reinforcement Learning with Internal Confidence AlignmentWithdrawn2.00
[PDF]ILLUMINATING THE PRESSURES THAT BREAK LLM AGENTS: EVOLUTIONARY SEARCH FOR ALIGNMENT THAT GENERALISESWithdrawn
[PDF]Repair the Action, Preserve the Intent: Minimal Feasibility Projection for Power-Grid AgentsWithdrawn1.33
[PDF]The Retrieval Paradox: Why RAG Fails Medical Vision-Language Models Across ArchitecturesWithdrawn1.00