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
2,657 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 575 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Offline Scores Overestimate Online Oversight: Timely Interception of LLM Agents with Causal-Cone Monitoring▼4.3k2.00
[PDF]Looking for Bidding Teammates: A Game-Theoretic Model of Stranger Collusion in Peer Review▼1.2k1.67
[PDF]Alleviating Semantic Narrowing in LLM Watermarking with Hamming-Neighborhood Acceptance▼4.5k2.67
[PDF]Dormant Agent: Stealthy Cross-Agent Attacks in VLM-Based Multi-Agent Systems via Emotion Steering▲3952.67
[PDF]CtrlFormer: Efficient Non-Interactive Secure Transformer Inference without Feature Explosion▲3952.67
[PDF]Gap-Adaptive Per-Objective Regularization against Differential Overoptimization in Multi-Objective Alignment▲3.0k2.33
[PDF]CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition▲3.0k2.33
[PDF]Locating, Removing, and Restoring: Auditing the Modular Account of Safety in Instruction-Tuned LLMs▼4.3k2.00
[PDF]Agents Recognize Source Inconsistency but Rarely Act on It: Decision-Time Mediation for Grounded Resolution▲14k3.00
[PDF]What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds▼4.3k2.00
[PDF]Query Complexity of Eliciting Consensus Lotteries with Bounded Adaptivity and Parallelism▲143.33
[PDF]Why LLM Agents Collapse Without Oversight: Measuring the Enforcement Gap in Reflexion-Style Agents▼1.2k1.67
[PDF]When the Editing Intent Is Split: A Cross-Modal Jailbreak Attack for Large Image Editing Models▲3952.67
Withdrawn or desk rejected (575)
[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