This study investigated whether robotic agents that deal with social hierarchical relationships can reduce the dominance of superiors and equalize participation among participants in discussions with hierarchical structures. Thirty doctors and students having hierarchical relationship were gathered as participants, and an intervention experiment was conducted using a robot that can encourage participants to speak depending on social hierarchy. These were compared with strategies that intervened equally for all participants without considering hierarchy and with a no-action. The robots performed follow actions, showing backchanneling to speech, and encourage actions, prompting speech from members with less speaking time, on the basis of the hierarchical relationships among group members to equalize participation. The experimental results revealed that the robot's actions could potentially influence the speaking time among members, but it could not be conclusively stated that there were significant differences between the robot's action conditions. However, the results suggested that it might be possible to influence speaking time without decreasing the satisfaction of superiors. This indicates that in discussion scenarios where experienced superiors are likely to dominate, controlling the robot's backchanneling behavior could potentially suppress dominance and equalize participation among group members.

Representational harms are widely recognized among fairness-related harms caused by generative language systems. However, their definitions are commonly under-specified. We present a framework, grounded in speech act theory (Austin, 1962), that conceptualizes representational harms caused by generative language systems as the perlocutionary effects (i.e., real-world impacts) of particular types of illocutionary acts (i.e., system behaviors). Building on this argument and drawing on relevant literature from linguistic anthropology and sociolinguistics, we provide new definitions stereotyping, demeaning, and erasure. We then use our framework to develop a granular taxonomy of illocutionary acts that cause representational harms, going beyond the high-level taxonomies presented in previous work. We also discuss the ways that our framework and taxonomy can support the development of valid measurement instruments. Finally, we demonstrate the utility of our framework and taxonomy via a case study that engages with recent conceptual debates about what constitutes a representational harm and how such harms should be measured.

For social animals like humans, it's critical to be able to recognize and react to the emotional state of others. One particularly important aspect of this ability is empathy--which, in this context, refers specifically to understanding when another person is in emotional distress. However, individuals can respond in very different ways to seeing someone in such distress. These responses fall into two broad categories. There are prosocial responses: reaching out to the person in distress to provide care and comfort.

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 anticipate emergent phenomena and potential risks. Drawing inspiration from the widely popular Stanford Prison Experiment, we contribute to this line of research by studying interaction patterns of LLM agents in a context characterized by strict social hierarchy. We do so by specifically studying two types of phenomena: persuasion and anti-social behavior in simulated scenarios involving a guard and a prisoner agent who seeks to achieve a specific goal (i.e., obtaining additional yard time or escape from prison). Leveraging 200 experimental scenarios for a total of 2,000 machine-machine conversations across five different popular LLMs, we provide a set of noteworthy findings. We first document how some models consistently fail in carrying out a conversation in our multi-agent setup where power dynamics are at play. Then, for the models that were able to engage in successful interactions, we empirically show how the goal that an agent is set to achieve impacts primarily its persuasiveness, while having a negligible effect with respect to the agent's anti-social behavior. Third, we highlight how agents' personas, and particularly the guard's personality, drive both the likelihood of successful persuasion from the prisoner and the emergence of anti-social behaviors. Fourth, we show that even without explicitly prompting for specific personalities, anti-social behavior emerges by simply assigning agents' roles. These results bear implications for the development of interactive LLM agents as well as the debate on their societal impact.

Agent-based models describing social interactions among individuals can help to better understand emerging macroscopic patterns in societies. One of the topics which is worth tackling is the formation of different kinds of hierarchies that emerge in social spaces such as cities. Here we propose a Bonabeau-like model by adding a second class of agents. The fundamental particularity of our model is that only a pairwise interaction between agents of the opposite class is allowed. Agent fitness can thus only change by competition among the two classes, while the total fitness in the society remains constant. The main result is that for a broad range of values of the model parameters, the fitness of the agents of each class show a decay in time except for one or very few agents which capture almost all the fitness in the society. Numerical simulations also reveal a singular shift from egalitarian to hierarchical society for each class. This behaviour depends on the control parameter $\eta$, playing the role of the inverse of the temperature of the system. Results are invariant with regard to the system size, contingent solely on the quantity of agents within each class. Finally, a couple of scaling laws are provided thus showing a data collapse from different model parameters and they follow a shape which can be related to the presence of a phase transition in the model.

Patterns of wins and losses in pairwise contests, such as occur in sports and games, consumer research and paired comparison studies, and human and animal social hierarchies, are commonly analyzed using probabilistic models that allow one to quantify the strength of competitors or predict the outcome of future contests. Here we generalize this approach to incorporate two additional features: an element of randomness or luck that leads to upset wins, and a "depth of competition" variable that measures the complexity of a game or hierarchy. Fitting the resulting model to a large collection of data sets we estimate depth and luck in a range of games, sports, and social situations. In general, we find that social competition tends to be "deep," meaning it has a pronounced hierarchy with many distinct levels, but also that there is often a nonzero chance of an upset victory, meaning that dominance challenges can be won even by significant underdogs. Competition in sports and games, by contrast, tends to be shallow and in most cases there is little evidence of upset wins, beyond those already implied by the shallowness of the hierarchy.

As the recently released GPT-3 and several recent studies demonstrate, racial bias, as well as bias based on gender, occupation, and religion, can be found in popular NLP language models. But a team of AI researchers wants the NLP bias research community to more closely examine and explore relationships between language, power, and social hierarchies like racism in their work. Published last week, the work, which includes analysis of 146 NLP bias research papers, also concludes that the research field generally lacks clear descriptions of bias and fails to explain how, why, and to whom that bias is harmful. "Although these papers have laid vital groundwork by illustrating some of the ways that NLP systems can be harmful, the majority of them fail to engage critically with what constitutes'bias' in the first place," the paper reads. "We argue that such work should examine the relationships between language and social hierarchies; we call on researchers and practitioners conducting such work to articulate their conceptualizations of'bias' in order to enable conversations about what kinds of system behaviors are harmful, in what ways, to whom, and why; and we recommend deeper engagements between technologists and communities affected by NLP systems."

Brain study from Google AI lab could help develop cyborgs that know where they stand in society's pecking order Participants had brain scans while learning about fictional company structures Then they had to identify which of two firms people worked at from their images Researchers believe that the way humans' brains work out their place in social hierarchies could be applied to intelligent robots in future Researchers believe that the way humans' brains work out their place in social hierarchies could be applied to intelligent robots in future Brain signals automatically tell us how humans fit into social hierarchies, according to new research. The findings could help build intelligent robots that know where they stand in the pecking order in relation to humans. After learning about the power structures, they were shown pictures of individuals from each company. From this, they had to decide which company the person worked for. 'We found that the way in which participants learn about the power of individuals was best explained by a process of Bayesian inference' said Dharshan Kumaran, a research scientist at DeepMind.

Testosterone gets a pretty bad reputation. It's been long known as the hormone of aggression. In his 1998 book, The Trouble With Testosterone: And Other Essays on the Biology of the Human Predicament, the neuroscientist Robert Sapolsky writes, "What evidence links testosterone with aggression? Some pretty obvious stuff": Males tend to have more testosterone than women, and tend to be more aggressive. "Times of life when males are swimming in testosterone (for example, after reaching puberty) correspond to when aggression peaks."