I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy

GM Campedelli, N Penzo, M Stefan, R Dessì… - arxiv preprint arxiv …, 2024 - arxiv.org
As Large Language Model (LLM)-based agents become increasingly autonomous and will
more freely interact with each other, studying interactions between them becomes crucial to …

Multilingual Trolley Problems for Language Models

Z **, M Kleiman-Weiner, G Piatti, S Levine… - … Workshop at NeurIPS …, 2024 - openreview.net
As large language models (LLMs) are deployed in more and more real-world situations, it is
crucial to understand their decision-making when faced with moral dilemmas. Inspired by a …