Research map / Large language models / AI and society
Norm Conflict Resolution in Stochastic Domains
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use weighted temporary norm suspension to choose which norms to violate | Norm conflict resolution in the vacuum cleaning MDP · Scenario 2: The Puddle | violation cost: 2.9701 vs. 200 | Helped |
| Prioritize the human-safety norm over the robot-safety norm | Norm conflict resolution in the vacuum cleaning MDP · Scenario 3: Broken Glass | violation cost: 200 vs. 5001 | Helped |
| Warn the human before leaving the hazardous glass uncleaned | Norm conflict resolution in the vacuum cleaning MDP · Scenario 4: Interrupting Phone Calls | violation cost: 103.96 | Helped |
| Temporarily suspend the cleaning duty rather than suspend it permanently | Norm conflict resolution in the vacuum cleaning MDP · Scenario 1: Business As Usual | duration of cleaning-duty suspension | Helped |
Closest papers by meaning
- Operationalising Rawlsian Ethics for Fairness in Norm Learning Agents (AAAI 2025 · similarity 0.86)
- Moral Alignment for LLM Agents (ICLR 2025 · similarity 0.85)
- MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning (AAAI 2026 · similarity 0.85)
- Evolving Interpretable Constitutions for Multi-Agent Coordination (ICML 2026 · similarity 0.84)
- An Evolutionary Perspective on AI Alignment (Student Abstract) (AAAI 2025 · similarity 0.83)
- Many LLMs Are More Utilitarian Than One (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.