MEW 2026

Table of Contents

• PDF
  
• Constructive Alignment: Governing Preference Dynamics in Human–AI Interaction 1-23 PDF
  Max Kanwal, Caryn Tran
• Bounded Morality: Defining the Space of Moral Computation 24-47 PDF
  Max Kanwal, Caryn Tran, Patrick Mineault
• Vertical Moral Growth for Robust Alignment: Perspective-Based Fine-Tuning Reduces Deception in Large Language Models 48-60 PDF
  Taichiro Endo
• Gender Bias in Emotion Recognition by Large Language Models 61-73 PDF
  Maureen Herbert, Katie Sun, Angelica Lim, Yasaman Etesam
• Learning from Mistakes: Can LLM Self-Recover after Misalignment? 74-83 PDF
  Olga E. Sorokoletova, Francesco Giarrusso, Vincenzo Suriani, Daniele Nardi
• Optimizing a Margin of Safety via Prompt Repair for Large Language Models 84-93 PDF
  Jessica Tang, Silviu Pitis, Sheila A. McIlraith
• Core Safety Values for Provably Corrigible Agents 94-107 PDF
  Aran Nayebi
• JETHICS: Japanese Ethics Understanding Evaluation Dataset 108-117 PDF
  Masashi Takeshita, Rafal Rzepka
• Governance Forms in the Age of Superintelligence: An Aristotelian Analysis 118-123 PDF
  Misaki Inoue
• Building Interpretable Models for Moral Decision-Making 124-131 PDF
  Mayank Goel, Aritra Das, Paras Chopra
• Invited Talk: Between Rules and Reasoning: Towards Machine Morality 133-133 PDF
  Elizaveta Tennant