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
17 results for “keyword:"emergent misalignment"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Mitigating Hidden Undesirable Behaviors from LLM Fine-Tuning via Consensus Distillation▲11k2.00
[PDF]Misaligned model variants serve as an effective source of training for harm detection probes▲5103.00
[PDF]The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment▲6.1k2.00
[PDF]Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors▲3.0k2.33
[PDF]What Survives Continued Training? A Longitudinal Benchmark for Emergent-Misalignment Defenses▼5.8k2.33
[PDF]Technique Awareness as an Alignment Risk: Model Familiarity of Inoculation Prompting Weakens its Effect▼1.2k3.00
Withdrawn or desk rejected (5)
[PDF]Shared Parametric Geometry and Data Provenance in Model Organisms for Emergent MisalignmentWithdrawn2.00