This paper investigates the factors fostering collective intelligence (CI) through a case study of *LinYi's Experiment, where over 2000 human players collectively controll an avatar car. By conducting theoretical analysis and replicating observed behaviors through numerical simulations, we demonstrate how self-organized division of labor (DOL) among individuals fosters the emergence of CI and identify two essential conditions fostering CI by formulating this problem into a stability problem of a Markov Jump Linear System (MJLS). These conditions, independent of external stimulus, emphasize the importance of both elite and common players in fostering CI. Additionally, we propose an index for emergence of CI and a distributed method for estimating joint actions, enabling individuals to learn their optimal social roles without global action information of the whole crowd.

Can social power endow social robots with the capacity to persuade? This paper represents our recent endeavor to design persuasive social robots. We have designed and run three different user studies to investigate the effectiveness of different bases of social power (inspired by French and Raven's theory) on peoples' compliance to the requests of social robots. The results show that robotic persuaders that exert social power (specifically from expert, reward, and coercion bases) demonstrate increased ability to influence humans. The first study provides a positive answer and shows that under the same circumstances, people with different personalities prefer robots using a specific social power base. In addition, social rewards can be useful in persuading individuals. The second study suggests that by employing social power, social robots are capable of persuading people objectively to select a less desirable choice among others. Finally, the third study shows that the effect of power on persuasion does not decay over time and might strengthen under specific circumstances. Moreover, exerting stronger social power does not necessarily lead to higher persuasion. Overall, we argue that the results of these studies are relevant for designing human--robot-interaction scenarios especially the ones aiming at behavioral change.

Artificial agents have traditionally been trained to maximize reward, which may incentivize power-seeking and deception, analogous to how next-token prediction in language models (LMs) may incentivize toxicity. So do agents naturally learn to be Machiavellian? And how do we measure these behaviors in general-purpose models such as GPT-4? Towards answering these questions, we introduce MACHIAVELLI, a benchmark of 134 Choose-Your-Own-Adventure games containing over half a million rich, diverse scenarios that center on social decision-making. Scenario labeling is automated with LMs, which are more performant than human annotators. We mathematize dozens of harmful behaviors and use our annotations to evaluate agents' tendencies to be power-seeking, cause disutility, and commit ethical violations. We observe some tension between maximizing reward and behaving ethically. To improve this trade-off, we investigate LM-based methods to steer agents' towards less harmful behaviors. Our results show that agents can both act competently and morally, so concrete progress can currently be made in machine ethics--designing agents that are Pareto improvements in both safety and capabilities.

This paper investigates how hate speech varies in systematic ways according to the identities it targets. Across multiple hate speech datasets annotated for targeted identities, we find that classifiers trained on hate speech targeting specific identity groups struggle to generalize to other targeted identities. This provides empirical evidence for differences in hate speech by target identity; we then investigate which patterns structure this variation. We find that the targeted demographic category (e.g. gender/sexuality or race/ethnicity) appears to have a greater effect on the language of hate speech than does the relative social power of the targeted identity group. We also find that words associated with hate speech targeting specific identities often relate to stereotypes, histories of oppression, current social movements, and other social contexts specific to identities. These experiments suggest the importance of considering targeted identity, as well as the social contexts associated with these identities, in automated hate speech classification.

The recently proposed DeGroot-Friedkin model describes the dynamical evolution of individual social power in a social network that holds opinion discussions on a sequence of different issues. This paper revisits that model, and uses nonlinear contraction analysis, among other tools, to establish several novel results. First, we show that for a social network with constant topology, each individual's social power converges to its equilibrium value exponentially fast, whereas previous results only concluded asymptotic convergence. Second, when the network topology is dynamic (i.e., the relative interaction matrix may change between any two successive issues), we show that each individual exponentially forgets its initial social power. Specifically, individual social power is dependent only on the dynamic network topology, and initial (or perceived) social power is forgotten as a result of sequential opinion discussion. Last, we provide an explicit upper bound on an individual's social power as the number of issues discussed tends to infinity; this bound depends only on the network topology. Simulations are provided to illustrate our results.

This paper analyses the DeGroot-Friedkin model for evolution of the individuals' social powers in a social network when the network topology varies dynamically (described by dynamic relative interaction matrices). The DeGroot-Friedkin model describes how individual social power (self-appraisal, self-weight) evolves as a network of individuals discuss a sequence of issues. We seek to study dynamically changing relative interactions because interactions may change depending on the issue being discussed. In order to explore the problem in detail, two different cases of issue-dependent network topologies are studied. First, if the topology varies between issues in a periodic manner, it is shown that the individuals' self-appraisals admit a periodic solution. Second, if the topology changes arbitrarily, under the assumption that each relative interaction matrix is doubly stochastic and irreducible, the individuals' self-appraisals asymptotically converge to a unique non-trivial equilibrium.