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
2,656 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 576 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Actions Speak Louder than Answers: Privileged-Context Self-Distillation for VLM Safety▼1.2k3.00
[PDF]Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring▲3.0k2.33
[PDF]Theory of Certified Unlearning for a Family of Regularization-Based Continual Learning▲5.4k3.00
[PDF]Linguistic Loopholes in LLM Unlearning: From a 174-Language–Script Benchmark to Coverage-Aware Unlearning▼4.5k2.67
[PDF]FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning▼1.2k1.67
[PDF]Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption▼5.8k2.33
[PDF]Directing Safety Signals to the Appropriate Neurons: Multilingual Safety Alignment through Selective Neuron Masking▲9.2k2.67
[PDF]Replication Is Not Specificity: Negative Controls for Representation-Based Reward-Hacking Detection▼1361.33
[PDF]Prompt Injection as an Information Channel: Detection Limits and Hierarchy Certificates▼4.3k2.00
[PDF]Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories▲9.2k2.67
[PDF]A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review▼5.8k2.33
[PDF]How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review▲3.0k2.40
[PDF]Exploiting Global Model Feedback: An Adaptive Model Poisoning Attack against Robust Federated Learning▼4.3k2.00
[PDF]DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models▲5103.00
[PDF]THE TROY MOMENT: HOW LLM AGENTS ADJUDICATE THE DECISION POINT UNDER IMPOSSIBLE TASKS, CLAIMED AUTHORITY, AND PEER INFORMATION▼4.3k2.00
[PDF]Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks▲3.0k2.33
Withdrawn or desk rejected (576)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected