Emergent social conventions and collective bias in LLM populations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910973462315008 |
|---|---|
| author | Ashery, Ariel Flint Aiello, Luca Maria Baronchelli, Andrea |
| author_facet | Ashery, Ariel Flint Aiello, Luca Maria Baronchelli, Andrea |
| contents | Social conventions are the backbone of social coordination, shaping how individuals form a group. As growing populations of artificial intelligence (AI) agents communicate through natural language, a fundamental question is whether they can bootstrap the foundations of a society. Here, we present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents. We then show how strong collective biases can emerge during this process, even when agents exhibit no bias individually. Last, we examine how committed minority groups of adversarial LLM agents can drive social change by imposing alternative social conventions on the larger population. Our results show that AI systems can autonomously develop social conventions without explicit programming and have implications for designing AI systems that align, and remain aligned, with human values and societal goals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08948 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Emergent social conventions and collective bias in LLM populations Ashery, Ariel Flint Aiello, Luca Maria Baronchelli, Andrea Multiagent Systems Artificial Intelligence Computers and Society Physics and Society Social conventions are the backbone of social coordination, shaping how individuals form a group. As growing populations of artificial intelligence (AI) agents communicate through natural language, a fundamental question is whether they can bootstrap the foundations of a society. Here, we present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents. We then show how strong collective biases can emerge during this process, even when agents exhibit no bias individually. Last, we examine how committed minority groups of adversarial LLM agents can drive social change by imposing alternative social conventions on the larger population. Our results show that AI systems can autonomously develop social conventions without explicit programming and have implications for designing AI systems that align, and remain aligned, with human values and societal goals. |
| title | Emergent social conventions and collective bias in LLM populations |
| topic | Multiagent Systems Artificial Intelligence Computers and Society Physics and Society |
| url | https://arxiv.org/abs/2410.08948 |