# The Elephant in the Room -- Why AI Safety Demands Diverse Teams

arXiv: https://arxiv.org/abs/2407.10254 · HTML: https://mlsanity.com/paper/2407.10254/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 10 of 10)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Emotional Intelligence of Large Language Models](https://mlsanity.com/paper/2307.09042/) (2023)
- [Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench](https://mlsanity.com/paper/2308.03656/) (2023)
- [Large Language Models as Superpositions of Cultural Perspectives](https://mlsanity.com/paper/2307.07870/) (2023)
- [AGI Safety Literature Review](https://mlsanity.com/paper/1805.01109/) (2018)

## Built on by (most cited first, 1 of 1)

- [The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims](https://mlsanity.com/paper/2506.02064/) (2025)

## Abstract (arXiv)

We consider that existing approaches to AI "safety" and "alignment" may not be using the most effective tools, teams, or approaches. We suggest that an alternative and better approach to the problem may be to treat alignment as a social science problem, since the social sciences enjoy a rich toolkit of models for understanding and aligning motivation and behavior, much of which could be repurposed to problems involving AI models, and enumerate reasons why this is so. We introduce an alternate alignment approach informed by social science tools and characterized by three steps: 1. defining a positive desired social outcome for human/AI collaboration as the goal or "North Star," 2. properly framing knowns and unknowns, and 3. forming diverse teams to investigate, observe, and navigate emerging challenges in alignment.