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139 results for “keyword:"llm safety"” in ICLR 2027. 20 withdrawn or desk rejected listed apart.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]Saturated Screening, Concentrated Cost: What a Full-Stack Ablation Table Reads in a Redundant Refusal Stack▼1.2k1.67
[PDF]Frozen Input-Harm Probes under Compression: Retained AUROC Does Not Mean Retained Refusal▼1.2k1.67
[PDF]SelfShield: Unlocking LLMs' Self-Protective Capability Against Jailbreak Attacks via a Resilient Anchor Layer▼5.8k2.33
[PDF]Defending Multi-turn Attacks On Large Language Models Through Active Intention Verification▲9.2k2.67
[PDF]Scalable Hierarchical Transformers for Multi-Turn Jailbreak Detection in Long Conversations▼1.2k1.67
[PDF]TotalGuardEval: Benchmark for Evaluating Guardrail Models on Underrepresented Risk Categories▼5.8k2.33
[PDF]TRAIL: Trajectory-Aware Navigation over Latent Hazard Landscapes for Multi-Turn LLM Jailbreaking▲3.0k2.33
[PDF]ACE-Guard: Automated Co-Evolutionary Guardrails for LLM Security via Inference-Time Natural Language Gradients▼1361.33
[PDF]How Robust Are Code Watermarks, Really? Rethinking Robustness Beyond Rule-Based Rewriting▼4.3k2.00
[PDF]From Dilution to Alignment: Understanding and Mitigating Long-Context Safety Degradation▼4.3k2.00
[PDF]K-Shield: Improving the Safety-Utility Trade-off in Refusal Steering with Local Null-Space Constraints▼4.5k2.67
[PDF]AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling▼5.8k2.33
[PDF]Do Jailbreaks Leave Identifiable Behavioral Footprints? Detection and Localization through Attention Occupancy▼4.3k2.00
[PDF]Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models▼4.5k2.67
[PDF]RIVET: Evaluating Retrieval-Induced Value Steering and Retrieval-Stage Mitigation in Search-Augmented LLMs▼1.2k1.67
[PDF]RefusalTrace: Localizing and Validating the Internal Refusal Pathway of LLMs with Sparse Autoencoder Features▲9.7k2.75
[PDF]Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning▲3.0k2.33
Withdrawn or desk rejected (20)
[PDF]CARVE: Coverage-Aware Reconciliation with Verified Evidence for Agent Skill DetectionDesk rejected2.20