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
24 results for “keyword:"language model safety"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reasoning Against Alignment: How Viewpoint Processing Destabilizes Safety Boundaries in Aligned LLMs▼1.2k1.67
[PDF]When Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations▲5.4k3.00
[PDF]Beyond Refuse-or-Comply: Fine-Grained Policy-to-Action Grounding in Safety-Aligned Language Models▼5.8k2.33
[PDF]BoundaryPlay: Improving Online Safety Self-Play via Counterfactual Request Construction▼4.3k2.00
[PDF]"Benign-Shifted Compliance": A Mechanistic Insight into Safety Behaviors of Diffusion Language Models under Adversarial Prefixes▲5.4k3.00
[PDF]Before the Refusal: Pre-Response Activation Signatures of False Refusal in Safety-Aligned Language Models▼1.2k1.67
[PDF]From Allow-or-Block to Risk-Adaptive Moderation: A Multi-Expert Safety Guardrail for Large Language Model Services▼5.8k2.33
[PDF]When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety▼5.8k2.33
[PDF]Actions Speak Louder than Answers: Privileged-Context Self-Distillation for VLM Safety▼1.2k3.00
Withdrawn or desk rejected (8)
[PDF]Which Image Property Carries The Jailbreak? A Controlled Dissection Of Image-To-Text JailbreaksWithdrawn1.67
[PDF]REFUSALTRACE: Sparse Activation Masking for Jailbreaking via Natural Refusal TrajectoriesWithdrawn2.00
[PDF]Beyond the Final Token: Detecting Jailbreak Prompts via Chat-Suffix-Probed Safety TrajectoriesWithdrawn1.67
[PDF]Raising the Bar for Chinese Adolescent LLM Safety: A Culturally-Grounded, Fine-Grained BenchmarkDesk rejected2.00