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979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart.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]Never Sampled, Always Accepted: Commitment Injection Through Top- Verification in Speculative Decoding▲3952.67
[PDF]Twenty-Five Samples to Blind a Guardrail: Stealthy Benign-Side Poisoning of Self-Adapting Safety Filters▲6.1k2.00
[PDF]The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces▼5.9k2.50
[PDF]Displaced but Recoverable: State-Transferable Safety Signals in Response-Prefilled Language Models▼4.3k2.00
[PDF]Benign Tasks, Unsafe Orders: The Local-to-Global Safety Gap in Continual LLM Fine-Tuning▼5.8k2.33
[PDF]After Denial, What Next? Recoverability-Aware Legal Continuation for Tool-Using Agents▼1.3k1.75
[PDF]Structure Becomes Signal: Document Hierarchy as a Learned Behavioral Channel in LLM Evaluators▼1.2k3.00
[PDF]SEFIR: Safety Detection in Frozen Multimodal Large Language Models via Internal Evidence Fusion▲3952.67
[PDF]FedPurifier: Proactive Distributed Experience Purification for Resilient Connected Autonomous Vehicle Platoons▲3.0k2.33
[PDF]MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair▼5.8k2.33
[PDF]When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety▼5.8k2.33
[PDF]FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding▼1.3k1.75
[PDF]DACPO: Drift-Adaptive Constrained Policy Optimization for Cue-Free Safety Recovery in Large Reasoning Models▲3952.67
[PDF]Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety–Helpfulness Alignment▼5.8k2.33
[PDF]Representation Without Disposition: Secret Loyalties Install as Preference but Not as Action, and What That Costs White-Box Audits▲3.0k2.33
[PDF]DarkPattern Teaming: Adaptive Discovery of LLM Dark Patterns in Multi-Turn Conversations▲5.4k3.00
[PDF]How Much Evaluation Is Enough? Risk-Aware Adaptive Evaluation (RAAE) of LLMs in High-Stakes Financial Applications▼1361.33
Withdrawn or desk rejected (231)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