paper-with-me

홈 › Papers

Emergent social conventions and collective bias in LLM populations

2024-10-11 · Ariel Flint Ashery, Luca Maria Aiello, Andrea Baronchelli

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.

📄 PDF Abstract BibTeX arXiv:2410.08948

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Reply to "Emergent LLM behaviors are observationally equivalent to data leakage"

2025-06-23 · Ariel Flint Ashery, Luca Maria Aiello, Andrea Baronchelli

A potential concern when simulating populations of large language models (LLMs) is data contamination, i.e. the possibility that training data may shape outcomes in unintended ways. While this concern is important and ma…

Conformity Generates Collective Misalignment in AI Agents Societies

2026-05-11 · Giordano De Marzo, Alessandro Bellina, Claudio Castellano, Viola Priesemann 외 arxiv

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override indivi…

Emergent LLM behaviors are observationally equivalent to data leakage

2025-05-26 · Christopher Barrie, Petter Törnberg

Ashery et al. recently argue that large language models (LLMs), when paired to play a classic "naming game," spontaneously develop linguistic conventions reminiscent of human social norms. Here, we show that their result…

Memorization

Emergent Dominance Hierarchies in Reinforcement Learning Agents

2024-01-21 · Ram Rachum, Yonatan Nakar, Bill Tomlinson, Nitay Alon 외

Modern Reinforcement Learning (RL) algorithms are able to outperform humans in a wide variety of tasks. Multi-agent reinforcement learning (MARL) settings present additional challenges, and successful cooperation in mixe…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Reinforcement Communication Learning in Different Social Network Structures

2020-07-19 · ICML Workshop LaReL 2020 7 · Marina Dubova, Arseny Moskvichev, Robert Goldstone

Social network structure is one of the key determinants of human language evolution. Previous work has shown that the network of social interactions shapes decentralized learning in human groups, leading to the emergence…

Multi-agent Reinforcement Learning