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2,656 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 576 withdrawn or desk rejected listed apart.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]The Sins of the Designer: Weight Generators Transmit Judge Bias to Models That Never Saw a Biased Example▼1.2k1.67
[PDF]SimAttack: A Simple and Effective Transferable Untargeted Adversarial Attack on Large Vision-Language Models▲6.1k2.00
[PDF]Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning▼4.3k2.00
[PDF]CICD-Guard: Contextual Intent Consensus for Robust Defense against LLM Jailbreak Attacks▼1361.33
[PDF]Cross-Encoder Fairness Degradation in Text-Attributed Graphs via Adversarial Node Injection▲9.2k2.67
[PDF]From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling▲3922.67
[PDF]Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models▲5103.00
[PDF]Hidden in Plain Pieces: Jailbreaking LVLM-based Embodied Agents via Compositional Environment Injection▲9.2k2.67
[PDF]Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation▲3922.67
[PDF]FedPRA: Policy-Residual Aggregation for Heterogeneous Differentially Private Federated Learning.▼4.3k2.00
[PDF]Learning the Wrong Lessons: Benchmarking Unsafe Experience Formation in Memory-Augmented Agents▼4.3k2.00
[PDF]Learning to Forget Together: Prompt-Conditioned Adapter Generation for Multi-Domain LLM Unlearning▼1.2k1.67
[PDF]Technique Awareness as an Alignment Risk: Model Familiarity of Inoculation Prompting Weakens its Effect▼1.2k3.00
[PDF]Sweeping Promptable Spoofs under the DirtyRAG: A Practical, Query-Blind RAG Attack Done Right▼4.3k2.00
[PDF]From Allow-or-Block to Risk-Adaptive Moderation: A Multi-Expert Safety Guardrail for Large Language Model Services▼5.8k2.33
Withdrawn or desk rejected (576)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