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
139 results for “keyword:"llm safety"” in ICLR 2027. 20 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Twenty-Five Samples to Blind a Guardrail: Stealthy Benign-Side Poisoning of Self-Adapting Safety Filters▲6.1k2.00
[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]Know Your Target before Striking: A Profile-Aware Adaptive Jailbreaking Framework for LLMs▼4.3k2.00
[PDF]DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection▲1.7k3.33
[PDF]Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs▼4.3k2.00
[PDF]Disentangling Safety and Capability in Large Language Models via Causal Interventional Decomposition▼1361.33
[PDF]Benign Safety Is Not a Robustness Certificate: Evidence of a Structural Evaluation Gap Across Attack Conditions▲11.00
[PDF]Adaptation or Poisoning? Security Risks of Conversational Test-Time Learning in Large Language Models▲3.0k2.33
[PDF]When Does Multi-Agent Debate Backfire? A Predictable and Preventable Failure Mode of Heterogeneous LLM Debate▼1611.50
[PDF]What Is a Conversation Made Of? A Reusable Semantic–Relational State Across Safety Tasks▲3.8k2.50
[PDF]SafetyFlip: Learning LLM Safety Boundaries from Bidirectional Counterfactual Instructions▲5103.00
[PDF]How to Tame a Multi-Headed Hydra? Adaptive Multi-Category Safety Steering for Large Language Models▲14k3.00
[PDF]Safe in Text, Unsafe in Action: Distinguishing Content and Physical Danger in LLM Hidden States▼4.5k2.67
[PDF]Locating, Removing, and Restoring: Auditing the Modular Account of Safety in Instruction-Tuned LLMs▼4.3k2.00
Withdrawn or desk rejected (20)
[PDF]CARVE: Coverage-Aware Reconciliation with Verified Evidence for Agent Skill DetectionDesk rejected2.20