mlsanityData to 14 Oct 2026

A theory of appropriateness with applications to generative artificial intelligence

arXiv 2412.19010 ↗First posted 26 Dec 2024cs.AIcited by 25

Not on the map. Why?

Abstract (arXiv)

What is appropriateness? Humans navigate a multi-scale mosaic of interlocking notions of what is appropriate for different situations. We act one way with our friends, another with our family, and yet another in the office. Likewise for AI, appropriate behavior for a comedy-writing assistant is not the same as appropriate behavior for a customer-service representative. What determines which actions are appropriate in which contexts? And what causes these standards to change over time? Since all judgments of AI appropriateness are ultimately made by humans, we need to understand how appropriateness guides human decision making in order to properly evaluate AI decision making and improve it. This paper presents a theory of appropriateness: how it functions in human society, how it may be implemented in the brain, and what it means for responsible deployment of generative AI technology.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Dec 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 15.

25 papers.

Sort:

By area:

  1. 2025Contextual Agent Security: A Policy for Every Purposecited by 59
  2. 2025Localized Cultural Knowledge is Conserved and Controllable in Large Language Modelscited by 20
  3. 2026Intelligent AI Delegationcited by 18
  4. 2026Colosseum: Auditing Collusion in Cooperative Multi-Agent Systemscited by 18
  5. 2025Jackpot! Alignment as a Maximal Lotterycited by 17
  6. 2025Generative Value Conflicts Reveal LLM Prioritiescited by 13
  7. 2025A Pragmatic View of AI Personhoodcited by 12
  8. 2025Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quiltcited by 9
  9. 2025SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combatcited by 9
  10. 2025Multi-Actor Generative Artificial Intelligence as a Game Enginecited by 8
  11. 2026Computational Hermeneutics: Evaluating generative AI as a cultural technologycited by 8
  12. 2025Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Valuecited by 6
13 more
  1. 2026Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contextscited by 6
  2. 2026Social physics in the age of artificial intelligencecited by 5
  3. 2026Positive Alignment: Artificial Intelligence for Human Flourishingcited by 5
  4. 2026Classroom AI: Large Language Models as Grade-Specific Teacherscited by 2
  5. 2026Solipsistic Superintelligence is Unlikely to be Cooperativecited by 1
  6. 2025Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictionscited by 0
  7. 2026Stabilising Generative Models of Attitude Changecited by 0
  8. 2026SCENE: Recognizing Social Norms and Sanctioning in Group Chatscited by 0
  9. 2026NoRA: Evaluating Grounded Reasonableness in Visual First-person Normative Action Reasoningcited by 0
  10. 2026LoSoNA: A Benchmark for Local Social Norm Adaptation in Group Conversationscited by 0
  11. 2026A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequencescited by 0
  12. 2026Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picturecited by 0
  13. 2026ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMscited by 0