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2,656 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 576 withdrawn or desk rejected listed apart.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]SEFIR: Safety Detection in Frozen Multimodal Large Language Models via Internal Evidence Fusion▲3922.67
[PDF]Resolving Score-Ordering Reversal in Watermarked Text: An Asymmetric Two-Sided Test for LLM Text Detection▲5103.00
[PDF]Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions▲3.0k2.33
[PDF]When Preference Margins Hide Text-Only Shortcuts: Visual-Conditional Margin Learning for Multimodal Reward Models▲5103.00
[PDF]H-MPO: Hierarchical Multi-Response Preference Optimization with Modality-Guided Decoding for Omni Large Language Models▼5.8k2.33
[PDF]SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation▲133.33
[PDF]Controllable Memory Evolution: Mitigating Memory Misevolution in LLM Agents via Relaxation▼1611.50
[PDF]DF-PRISM: Beyond Aggregate Metrics via Visual-Attribute Profiling for Deepfake Detectors▼4.3k2.00
[PDF]From Textual Outputs to Probabilistic Signatures: Robust Black-Box Model Ownership Verification▲14k3.00
[PDF]FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding▼1.3k1.75
[PDF]DACPO: Drift-Adaptive Constrained Policy Optimization for Cue-Free Safety Recovery in Large Reasoning Models▲3922.67
[PDF]Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety–Helpfulness Alignment▼5.8k2.33
[PDF]Multi-Round SPEAR++: Exact Data Reconstruction from Model Updates across communication rounds in Federated Learning▼4.3k2.00
[PDF]ECLIPSE: Orthogonal Subspace Projection for Triggerless Bias Injection in Diffusion Models▼1.2k1.67
[PDF]TRACE: Evidence-Grounded Epistemic Control for Reliable Autonomous Penetration Testing▼5.8k2.33
[PDF]Representation Without Disposition: Secret Loyalties Install as Preference but Not as Action, and What That Costs White-Box Audits▲3.0k2.33
[PDF]DarkPattern Teaming: Adaptive Discovery of LLM Dark Patterns in Multi-Turn Conversations▲5.4k3.00
Withdrawn or desk rejected (576)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