Large Language Models can Achieve Social Balance

• URL: http://arxiv.org/abs/2410.04054v2
• Date: Sat, 15 Mar 2025 01:10:55 GMT
• Title: Large Language Models can Achieve Social Balance
• Authors: Pedro Cisneros-Velarde,
• Abstract summary: Social balance dictates how individual interactions can lead a population to become one faction of positive interactions or be divided in two or more antagonistic factions.<n>We consider a group of large language models (LLMs) and study how, after continuous interactions, they can achieve social balance.<n>We find that achieving social balance depends on (i) the type of interaction; (ii) whether agents consider homophily or influence from their peers; and (iii) the population size.
• Score: 2.8282906214258805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Social balance is a well-established concept in sociology which dictates how individual interactions can lead a population to become one faction of positive interactions or be divided in two or more antagonistic factions. In this paper, we consider a group of large language models (LLMs) and study how, after continuous interactions, they can achieve social balance. Across three different LLM models, we find that achieving social balance depends on (i) the type of interaction; (ii) whether agents consider homophily or influence from their peers; and (iii) the population size. We characterize how each model achieves social balance with different frequency, diversity of positive or negative interactions, and interaction stability across conditions (i) to (iii). We show that models achieve different notions of social balance and justify their social dynamics differently. Remarkably, the largest model is not necessarily more likely to achieve social balance with more frequency, stability, and diversity than the smaller ones.

Related papers

• SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users [70.02370111025617]
  We introduce SocioVerse, an agent-driven world model for social simulation. Our framework features four powerful alignment components and a user pool of 10 million real individuals. Results demonstrate that SocioVerse can reflect large-scale population dynamics while ensuring diversity, credibility, and representativeness.
  arXiv  Detail & Related papers  (2025-04-14T12:12:52Z)
• SocialGen: Modeling Multi-Human Social Interaction with Language Models [30.068879125411726]
  We introduce SocialGen, the first unified motion-language model capable of modeling interaction behaviors among varying numbers of individuals. Unlike prior methods that are limited to two-person interactions, we propose a novel social motion representation that supports tokenizing the motions of an arbitrary number of individuals. This alignment enables the model to leverage rich, pretrained linguistic knowledge to better understand and reason about human social behaviors.
  arXiv  Detail & Related papers  (2025-03-28T22:57:25Z)
• Social Genome: Grounded Social Reasoning Abilities of Multimodal Models [61.88413918026431]
  Social Genome is the first benchmark for fine-grained, grounded social reasoning abilities of multimodal models. It contains 272 videos of interactions and 1,486 human-annotated reasoning traces related to inferences about these interactions. Social Genome is also the first modeling challenge to study external knowledge in social reasoning.
  arXiv  Detail & Related papers  (2025-02-21T00:05:40Z)
• The Dynamics of Social Conventions in LLM populations: Spontaneous Emergence, Collective Biases and Tipping Points [0.0]
  We investigate the dynamics of conventions within populations of Large Language Model (LLM) agents using simulated interactions. We show that globally accepted social conventions can spontaneously arise from local interactions between communicating LLMs. Minority groups of committed LLMs can drive social change by establishing new social conventions.
  arXiv  Detail & Related papers  (2024-10-11T16:16:38Z)
• SocialGaze: Improving the Integration of Human Social Norms in Large Language Models [28.88929472131529]
  We introduce the task of judging social acceptance. Social acceptance requires models to judge and rationalize the acceptability of people's actions in social situations. We find that large language models' understanding of social acceptance is often misaligned with human consensus.
  arXiv  Detail & Related papers  (2024-10-11T10:35:58Z)
• Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis [23.329280888159744]
  Large Language Models (LLMs) perpetuate social biases, reflecting prejudices in their training data and reinforcing societal stereotypes and inequalities. We propose a unique debiasing technique, Social Contact Debiasing (SCD), that instruction-tunes these models with unbiased responses to prompts. Our research demonstrates that LLM responses exhibit social biases when subject to contact probing, but more importantly, these biases can be significantly reduced by up to 40% in 1 epoch of instruction tuning LLaMA 2 following our SCD strategy.
  arXiv  Detail & Related papers  (2024-07-02T07:58:46Z)
• Social learning with complex contagion [0.49109372384514843]
  We introduce a mathematical model that combines the concepts of complex contagion with payoff-biased imitation. Our framework generalizes traditional models of social learning by imitation. It provides a synthetic framework that describes more realistic forms of behavioral change in social systems.
  arXiv  Detail & Related papers  (2024-06-21T07:32:58Z)
• SocialBench: Sociality Evaluation of Role-Playing Conversational Agents [85.6641890712617]
  Large language models (LLMs) have advanced the development of various AI conversational agents. SocialBench is the first benchmark designed to evaluate the sociality of role-playing conversational agents at both individual and group levels. We find that agents excelling in individual level does not imply their proficiency in group level.
  arXiv  Detail & Related papers  (2024-03-20T15:38:36Z)
• Do LLM Agents Exhibit Social Behavior? [5.094340963261968]
  State-Understanding-Value-Action (SUVA) is a framework to systematically analyze responses in social contexts. It assesses social behavior through both their final decisions and the response generation processes leading to those decisions. We demonstrate that utterance-based reasoning reliably predicts LLMs' final actions.
  arXiv  Detail & Related papers  (2023-12-23T08:46:53Z)
• SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents [107.4138224020773]
  We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and humans. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We find that GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills.
  arXiv  Detail & Related papers  (2023-10-18T02:27:01Z)
• Training Socially Aligned Language Models on Simulated Social Interactions [99.39979111807388]
  Social alignment in AI systems aims to ensure that these models behave according to established societal values. Current language models (LMs) are trained to rigidly replicate their training corpus in isolation. This work presents a novel training paradigm that permits LMs to learn from simulated social interactions.
  arXiv  Detail & Related papers  (2023-05-26T14:17:36Z)
• Flexible social inference facilitates targeted social learning when rewards are not observable [58.762004496858836]
  Groups coordinate more effectively when individuals are able to learn from others' successes. We suggest that social inference capacities may help bridge this gap, allowing individuals to update their beliefs about others' underlying knowledge and success from observable trajectories of behavior.
  arXiv  Detail & Related papers  (2022-12-01T21:04:03Z)
• SSAGCN: Social Soft Attention Graph Convolution Network for Pedestrian Trajectory Prediction [59.064925464991056]
  We propose one new prediction model named Social Soft Attention Graph Convolution Network (SSAGCN) SSAGCN aims to simultaneously handle social interactions among pedestrians and scene interactions between pedestrians and environments. Experiments on public available datasets prove the effectiveness of SSAGCN and have achieved state-of-the-art results.
  arXiv  Detail & Related papers  (2021-12-05T01:49:18Z)
• PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception [50.551003004553806]
  We create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions. Phase is validated with human experiments demonstrating that humans perceive rich interactions in the social events. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE, which outperforms state-of-the-art feed-forward neural networks.
  arXiv  Detail & Related papers  (2021-03-02T18:44:57Z)
• COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering [50.65816570279115]
  Identification of the implicit causes and effects of a social context is the driving capability which can enable machines to perform commonsense reasoning. Current approaches in this realm lack the ability to perform commonsense reasoning upon facing an unseen situation. We present Conditional SEQ2SEQ-based Mixture model (COSMO), which provides us with the capabilities of dynamic and diverse content generation.
  arXiv  Detail & Related papers  (2020-11-02T07:08:19Z)
• Interactions in information spread: quantification and interpretation using stochastic block models [3.5450828190071655]
  In social networks, users' behavior results from the people they interact with, news in their feed, or trending topics. Here, we propose a new model, the Interactive Mixed Membership Block Model (IMMSBM), which investigates the role of interactions between entities. In inference tasks, taking them into account leads to average relative changes with respect to non-interactive models of up to 150% in the probability of an outcome.
  arXiv  Detail & Related papers  (2020-04-09T14:22:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.