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2,656 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 576 withdrawn or desk rejected listed apart.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]Gradient-Guided Radioactive Watermarking for Detecting Fine-Tuning on Teacher-Generated Data▼4.5k2.67
[PDF]Rethinking Safety Reward Models in Long-Context Settings: Systematic Evaluation and Reliable Contextual Modeling▲9.2k2.67
[PDF]When Backdoors Meet Selective State Spaces: Mechanisms and Attacks in Mamba Language Models▲15k3.50
[PDF]Human Modeling Meets AI Metacognition: Toward Coupled Cognitive Alignment for Interactive Agents▼1.2k1.67
[PDF]Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation▲3.0k2.33
[PDF]They Know When They're Unsure: Confidence-Gated Acceptance as a Two-Sided Defense against Sycophancy in Video Language Models▼1.2k1.67
[PDF]Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs▼4.3k2.00
[PDF]Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment▼1.2k1.67
[PDF]Linear Separability Is Not Input Controllability: Intermediate-Layer Jailbreak on VLMs▲6.1k2.00
[PDF]Boosting Diversity and Relevance: Privacy-Preserving Demonstration Synthesis for In-Context Learning▼5.8k2.33
[PDF]SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors▼4.5k2.67
[PDF]Can a Backdoor Span Source and Wireless Domains? A Cross-Domain Backdoor Attack on Semantic Communication▲9.2k2.67
[PDF]Beyond First-Order Feature Alignment: Second-Order Subspace Alignment for Adversarial Attacks on Closed-Source MLLMs▲3.0k2.33
[PDF]PRISM: Causal Counterfactual Minimization of Agent Tool Privileges via Information Bottleneck Role Induction▼4.3k2.00
[PDF]Minority Welfare Under LLM-Governed Allocation: A Systematic Empirical and Mechanistic Study▼1361.33
[PDF]Guarding a Needle in the Haystack: A Real-Time Policy-Following Streaming Video Guardrail▲3922.67
Withdrawn or desk rejected (576)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