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2,656 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 576 withdrawn or desk rejected listed apart.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]InterMind: What Happens Between Minds? Benchmarking Theory of Mind Across Human–AI Interaction▼1.2k1.67
[PDF]What Survives Continued Training? A Longitudinal Benchmark for Emergent-Misalignment Defenses▼5.8k2.33
[PDF]From Post-Training Plasticity to Function-Targeted Adaptation in Large Language Models▼4.3k2.00
[PDF]How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social Network▼4.3k2.00
[PDF]PLM-CARE: Biosafety Assessment and Quality-Matched Preference Alignment for Protein Language Models▼4.3k2.00
[PDF]Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering▼4.3k2.00
[PDF]PonderAgent: A Risk-Adaptive Dual-System Framework for Safe and Selective Mobile GUI Agents▲11.00
[PDF]BlindClean: A Prior-Knowledge-Free Data Sanitization Method against Clean-Label Backdoor Attacks▼1361.33
[PDF]Activation Is Not Specificity: Structural Trajectory Backdoors in Tool-Calling LLM Agents▼4.3k2.00
[PDF]Linguistic Cartography: Metric Spatial and Hierarchical Platial Representations in Language Models▲5103.00
[PDF]Cooperative Words, Adversarial Actions: Action-Level Ambiguity in Embodied Multi-Agent Systems▼13k2.00
[PDF]The System Is Manipulated. Are You? Assessing the Downstream Impact of Manipulated LLM Decision Support▲3912.67
[PDF]StateHazard-MM: A Benchmark for Selective Unlearning of State-Dependent Hazards in Multimodal Models▼5.8k2.33
[PDF]PABP: An Approximately Truthful Auction Mechanism for Federated Learning with Bid Privacy Protection▲3912.67
[PDF]RoboTopo: Inferring Hidden Communication Topology in LLM-Controlled Multi-Robot Systems▼4.5k2.67
[PDF]Efficient Deterministic Truncation and RMFE-Native Fixed-Point Operators for Private Neural Network Training▲6.1k2.00
[PDF]Beyond Text-to-Image: Unified Erasure of Sexually Explicit Content in Diffusion Models▼4.5k2.67
[PDF]BlameShift: Blame Integrity of Multi-Agent Failure Attribution under Ownership-Constrained Narrative Edits▼1361.33
[PDF]Right Answer, Wrong Reasoning: Localizing Chain-of-Thought Restoration Errors in the Residual Stream▲3912.67
[PDF]When Delimiters Mislead: Visual-Text Regrounding for Multi-Image Hallucination Mitigation▲5103.00
[PDF]AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling▼5.8k2.33
[PDF]CogRef: Cognitive Reflection for Hallucination Mitigation in Multimodal Large Language Models▲5103.00
[PDF]MT-NPO: Modality-Aware Token-Level Negative Preference Optimization for MLLM Unlearning▼2093.50
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