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2,656 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 576 withdrawn or desk rejected listed apart.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]LLM Agent Refusal Can be Harmful: An Availability Attack through MITM Tampering on Remote MCP Services▼4.3k2.00
[PDF]SPEAR: Privacy- and Executability-Aware Subquery Routing for Edge-Cloud Collaborative RAG▼4.3k2.00
[PDF]When Does an Edit Become Unsafe? Tracing Safety Emergence Along the Generative Trajectory of Image Editing Models▼4.3k2.00
[PDF]Optimizing the Ineffable: Generative Policy Learning for Human-Centered Decision-Making▼4.3k2.00
[PDF]Globally coordinated sample reweighting for fair federated learning under heterogeneity▲13k2.33
[PDF]JailbreakProfiler: Fine-Grained Attack Pattern Recognition and Open-Set Attribution for LLM Safety▼5.8k2.33
[PDF]Beyond Refusal: Policy-Grounded On-Policy Distillation for Safety Decisions and Recovery▼1.2k1.67
[PDF]Safety Is Not Conserved: Constraining Self-Improvement Across Models and Agent Harnesses▼1361.33
[PDF]Pseudo group-guided and reliability-aware debiasing framework for unsupervised bias mitigation▼5.8k2.33
[PDF]ORBIT: EFFICIENT VERIFICATION OF EDITED LLM OUTPUTS WITH COMPACT ROUTING HINTS AND LOCAL SEMANTIC ASSESSMENT▼1.3k1.75
[PDF]When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels▲5.4k3.00
[PDF]Steering Language Models Without Contrastive Pairs via Unsupervised Latent Region Matching▼1361.33
[PDF]Which Graph Is Safest? Predicting Adversarial Capture of LLM Agent Groups from Local Kernels▼4.3k2.00
[PDF]ModEval: Benchmarking Steering Modifiers for Social-Risk Evaluation in Text-to-Image Generation▼5.8k2.33
[PDF]When LLM Advice Depends on Values Users Never Stated: Measuring Undisclosed Preference Dependence▼1.2k1.67
[PDF]ResSub: Dual-Level Backdoor Defense via Residual Alignment and Subspace Perturbation in Vertical Federated Learning▲13k2.33
[PDF]Detecting Model Poisoning Attacks in Federated Learning via Joint Spatio-Temporal Inspection▼4.3k2.00
[PDF]Yours or Mine? Misleading Latent Diffusion Model Attribution via Cross-Model Reconstruction▲5.4k3.00
[PDF]Beyond a Single Attack: Generalizable Backdoor Detection via Single-Attack Meta-Classification▼4.3k2.00
[PDF]From Declared Capabilities to Behavior: Detecting Malicious Agent Skills Through Consistency Analysis▲9.2k2.67
Withdrawn or desk rejected (576)
[PDF]A Review of Indirect Prompt Injection and its Defenses Using Large-Scale Public Red-Teaming Competition DataWithdrawn2.00
[PDF]Faithfulness Anchoring as Defense Against CoT Hijacking: A Mechanism-First Approach via Residual-Stream AnalysisWithdrawn1.33
[PDF]RELATE : An Evaluation Framework for Measuring Relational Orientation of Large Language ModelsWithdrawn1.67
[PDF]Characterizing When Language Models Take Harmful Actions to Protect Their Assigned GoalsWithdrawn2.00