Measuring narrative polarization in online discourse by Jan Elfes, Marco Bastos, and Luca Maria Aiello, published in PNAS Nexus.

We introduce narrative polarization as diverging representations of key actors through their positioning in popular narratives. For example, a representation of Palestinians as a people striving for rights and of Israel as a violent actor favors interpretations of violent actions by Palestinians as resistance. In contrast, a focus on the struggle of Jews to escape historical persecution and of Palestinian groups as a constant violent threat might render the same actions as terrorism. Such structural differences in how actors are positioned shape the information landscapes that audiences navigate and affect their opinions. We showcase this by measuring narrative polarization around the Israeli-Palestinian conflict on YouTube. We find that, while videos produce highly polarized narratives, comments converge on a shared narrative distribution, offering less polarized narrative representations.

Group size effects and collective misalignment in LLM multi-agent systems by Ariel Flint, Luca Maria Aiello, Romualdo Pastor-Satorras, and Andrea Baronchelli, published in PNAS.

As AI agents begin to operate in populations rather than one at a time, our new research suggests that the number of them changes what they collectively decide — amplifying a bias, inventing one from nothing, or flipping a group into the opposite of what each agent would choose alone. When artificial intelligence (AI) agents interact in groups, their number is not merely a technical detail. It is a decisive factor in what the group settles on: populations built from the same AI model, doing the same task, can reach opposite outcomes for no other reason than that one group is bigger.

In this work, we experimented with populations of LLM agents playing the “naming game”, a classic framework for studying how conventions emerge, in which randomly paired agents each pick a word from a shared pool and are rewarded when they happen to pick the same one. Agents see only their own recent interactions, never the wider population, and are never told they are in a group. Over many pairings, a population can converge spontaneously on a shared convention.

We found that interactions can pull a group away from what its members individually want in three ways. It can amplify an existing leaning until the group converges on it almost every time. It can induce a preference out of nothing, with populations of individually neutral agents reliably favouring one word over an equally viable alternative. And it can reverse a preference outright, so that a population settles on the word its own members disfavoured. Group size then determines how strongly these preferences bite, in ways that cannot be extrapolated. Larger populations became more predictable across every model and word pair tested, converging on one word until the outcome was effectively certain. But the size at which that tipping point arrived varied enormously: for some combinations as few as two agents, for others around ten thousand.

Overall, our results demonstrate that more is different for LLM populations: The number of interacting agents is a key driver of the dynamics, with implications for the design and governance of multi-agent AI systems.

Unmasking conversational bias in AI multiagent systems by Erica Coppolillo, Giuseppe Manco, and Luca Maria Aiello, published in PLOS One.

New paper on PLOS One by Luca Aiello Detecting biases of generative AI is critical, but it is often done considering models in isolation. In particular, biases emerging from interactions among conversational agents remain largely unexplored. In this paper we present a framework designed to quantify biases within multi-agent systems of conversational agents. We simulate echo chambers where agents are initialized with aligned perspectives on a polarizing topic and asked to develop the topic in multi-turn discussions. Surprisingly, we observe that, despite the echo-chamber setting, the agent stance shifts away from their initial position, often towards liberal positions. Crucially, the bias observed in these echo-chamber experiments remains undetected by traditional bias detection methods that probe models in isolation. This highlights a critical need for the development of a more sophisticated toolkit for bias detection and mitigation for AI multi-agent systems.