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
39 results for “keyword:"safety evaluation"” in ICLR 2027. 20 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]The Signal Survives, the Threshold Slips: Small LLM Agents After Quantization and Fine-Tuning▼1.2k1.67
[PDF]A Falsification Study of Coupled-Constraint Telemetry Diagnostics in Multi-Agent Learning▼1361.33
[PDF]On the Framing Effect of AI Red-Teaming Instructions: Evidence from Prior Exercises and Controlled Simulations▼4.3k2.00
[PDF]AeroCopilotBench: Safety-Gated Evaluation of LLM Agents on Aircraft Emergency Procedures in an Executable Cockpit▲3.0k2.50
[PDF]Beyond Refuse-or-Comply: Fine-Grained Policy-to-Action Grounding in Safety-Aligned Language Models▼5.8k2.33
[PDF]LIBERO-Risk: Safety-Critical Scenario Generation and Process-Level Evaluation for Vision-Language-Action Models▲3.0k2.33
[PDF]MedicalPressureBench: Evaluating Care Pathway Integrity of Medical Agents Under Workplace Pressure▼4.3k2.00
[PDF]Frozen Input-Harm Probes under Compression: Retained AUROC Does Not Mean Retained Refusal▼1.2k1.67
[PDF]Are Your Agents Ready to Evolve? Assessing Evolution-Readiness in Agents Through Paired Safety and Utility Scoring▲3.0k2.33
[PDF]THE JUDGE LOTTERY: DIAGNOSING WHETHER COMPARISONS BETWEEN STOCHASTIC LLM JUDGES ARE ADEQUATELY SUPPORTED BY RESAMPLING EVIDENCE▼1361.33
[PDF]AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making▼1.2k1.67
[PDF]DART: Defense-Aware Red Teaming with a Critical Cue Bank for Open-World Adversarial Evaluation▼5.8k2.33
[PDF]Every Guardrail Has a Floor: Deployment Limits of Action Guardrails from the Summary They Read▼4.3k2.00
[PDF]Seeing Safety Across Languages: Disentangling Multilingual Safety from Visual-Language Failures in Multimodal Large Language Models▼1361.33
Withdrawn or desk rejected (20)
[PDF]Prediction Is Not All You Need: TraceGuard for Action-Oriented Safety Evaluation of Long-Horizon AgentsDesk rejected
[PDF]Diagnosing Poisoning Effects in Adapted LLM Guardrails: Beyond Fixed-Threshold EvaluationDesk rejected
[PDF]MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android AppsDesk rejected2.67
[PDF]PAIRBench: Complete Response-Function Coverage for Auditing Policy-Conditioned Safety GuardsWithdrawn1.33
[PDF]SameFact: The Same Safety Facts Lead to Different Responses Across Different InterfacesDesk rejected2.33
[PDF]Raising the Bar for Chinese Adolescent LLM Safety: A Culturally-Grounded, Fine-Grained BenchmarkDesk rejected2.00