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362 results for “keyword:"ai safety"” in ICLR 2027. 80 withdrawn or desk rejected listed apart.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]Replication Is Not Specificity: Negative Controls for Representation-Based Reward-Hacking Detection▼1361.33
[PDF]DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models▲5103.00
[PDF]SAE Interventions Can Be Unreliable: Post-Intervention Recovery of Suppressed Behavior▼4.3k2.00
[PDF]Balanced Perturbation and Subspace Erasure Do Not Identify What an Activation Monitor Reads▼1.2k1.67
[PDF]Pressure Is Not Enough: A Causal Test of Whether Optimization Induces Encoded Chain-of-Thought▼1.2k1.67
[PDF]When Recovery Creates Resistance: Instrumental Shutdown Avoidance from Gridworlds to Language-Model Agents▼5.3k1.33
[PDF]CONFORMALGUARD: DISTRIBUTION-FREE FALSEBLOCK GUARANTEES FOR MULTI-AGENT LLM SYSTEMS VIA CONFORMAL PREDICTION ON DYNAMIC EXECUTION GRAPHS▼3.7k2.25
[PDF]Every Guardrail Has a Floor: Deployment Limits of Action Guardrails from the Summary They Read▼4.3k2.00
[PDF]Information Flow Is Not Execution Authority: A Controlled Evaluation of LLM Multi-Agent Systems▼4.3k2.00
[PDF]CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement▼4.5k2.67
[PDF]What does lie-detection accuracy measure? An Identification Audit of behavioural LLM deception benchmarks▼71.25
[PDF]Measuring Say-Do Consistency in Tool-Using Agents: A Claim-Execution Traceability Framework▼1.2k1.67
[PDF]Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning▼1361.33
[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
Withdrawn or desk rejected (80)
[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]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00