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
979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CAST: Community-Adaptive Social Red-Teaming of LLM-Agent Societies via Population-Level Preference Optimization▼5.8k2.33
[PDF]Data-Driven Safety Verification of POMDPs: Showing Learnability of Safety Certificates via Spectral Learning of Weighted Automata▼4.3k2.00
[PDF]Spectrally Broad, Behaviorally Compressible: Functional Cores of Safety-Tuning Updates and What Downstream Fine-Tuning Does to Them▲3.0k2.33
[PDF]Mechanism-Preserving LoRA: Causal Internal Constraints for Capability-Preserving Detoxification▲13k2.33
[PDF]StegoBench: Evaluating steganography potential in language models through supervised learning▲3.0k2.50
[PDF]FSPO: Fast Adversarial Training against Jailbreak Attacks via Soft Prompt Optimization▼4.5k2.67
[PDF]Consistency Loss Is Secretly Picking a Side: Risk-Directed Consensus for High-Stakes Decisions▼1.2k1.67
[PDF]CROSS: Coupled Recurrence of Latent-Symbolic Security-State for Runtime Safety Monitoring of AI Agents▼5.8k2.33
[PDF]The Announcement, Not the Attack: What LLM Safety Judges Answer and What Their Hidden States Hold▲5.4k3.00
[PDF]AEGIS: Evidence-Grounded Agent Safety Verification with Diffusion Scoring and Ising-Structured Risk Inference▼4.3k2.00
[PDF]Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters▼4.5k2.67
[PDF]PACT: Provenance-Aware Contract Testing — What Do LLM-Agent Task-Contract Checkers Actually Certify?▼1361.33
[PDF]AeroCopilotBench: Safety-Gated Evaluation of LLM Agents on Aircraft Emergency Procedures in an Executable Cockpit▲3.0k2.50
[PDF]Breaking the Refusal Barrier: Stochastic Discovery of Residual Unsafe Behaviors in Aligned Language Models▼4.3k2.00
Withdrawn or desk rejected (231)
[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]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00