相关论文: Investigating social alignment via mirroring in a …

Language interfaces with many other cognitive domains. This paper explores how interactions at these interfaces can be studied with deep learning methods, focusing on the relation between language emergence and visual perception. To model…

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of…

Modeling social interactions is a challenging task that requires flexible frameworks. For instance, dissimulation and externalities are relevant features influencing such systems -- elements that are often neglected in popular models. This…

Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with…

In human societies, people's willingness to compete and strive for better social status as well as being envious of those perceived in some way superior lead to social structures that are intrinsically hierarchical. Here we propose an…

Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on…

Cognitive biases often shape human decisions. While large language models (LLMs) have been shown to reproduce well-known biases, a more critical question is whether LLMs can predict biases at the individual level and emulate the dynamics of…

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Large Language Models (LLMs) have revolutionized Natural Language Processing but exhibit limitations, particularly in autonomously addressing novel challenges such as reasoning and problem-solving. Traditional techniques like…

Many empirical networks are intrinsically pluralistic, with interactions occurring within groups of arbitrary agents. Then the agent in the network can be influenced by types of neighbors, common examples include similarity, opposition, and…

We propose a formalism to model and reason about reconfigurable multi-agent systems. In our formalism, agents interact and communicate in different modes so that they can pursue joint tasks; agents may dynamically synchronize, exchange…

The study of social emergence has long been a central focus in social science. Traditional modeling approaches, such as rule-based Agent-Based Models (ABMs), struggle to capture the diversity and complexity of human behavior, particularly…

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

Artificial intelligence systems increasingly involve continual learning to enable flexibility in general situations that are not encountered during system training. Human interaction with autonomous systems is broadly studied, but research…

Humans do not always make rational choices, a fact that experimental economics is putting on solid grounds. The social context plays an important role in determining our actions, and often we imitate friends or acquaintances without any…

Effective collaboration in multi-agent systems requires communicating goals and intentions between agents. Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter-module communication,…

Social dilemmas have been widely studied to explain how humans are able to cooperate in society. Considerable effort has been invested in designing artificial agents for social dilemmas that incorporate explicit agent motivations that are…

Multi-agent models often describe populations segregated either in the physical space, i.e. subdivided in metapopulations, or in the ecology of opinions, i.e. partitioned in echo chambers. Here we show how the interplay between homophily…

The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific…

Large language models (LLMs) inherit biases from their training data and alignment processes, influencing their responses in subtle ways. While many studies have examined these biases, little work has explored their robustness during…