Related papers: Human Choice Prediction in Language-based Persuasi…
As large language model (LLM) agents become more prevalent in real world social settings, social intelligence will play an increasingly critical role. But social intelligence is still a poorly defined construct, for humans and artificial…
Simulation is an invaluable tool for developing and evaluating controllers for self-driving cars. Current simulation frameworks are driven by highly-specialist domain specific languages, and so a natural language interface would greatly…
Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes, with profound implications for their trustworthy adoption in research and society. Game theory offers…
With the software industry shifting toward a data-driven culture, online A/B testing is a key tool for evaluating new technologies. However, deploying such experiments requires substantial resources, may negatively impact users, and…
In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment.…
The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose…
As Large Language Model (LLM)-based agents increasingly engage with human society, how well do we understand their prosocial behaviors? We (1) investigate how LLM agents' prosocial behaviors can be induced by different personas and…
Computational experiments have emerged as a valuable method for studying complex systems, involving the algorithmization of counterfactuals. However, accurately representing real social systems in Agent-based Modeling (ABM) is challenging…
Large language models (LLMs) are increasingly deployed to support human decision-making. This use of LLMs has concerning implications, especially when their prescriptions affect the welfare of others. To gauge how LLMs make social…
Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…
We introduce Open-Universe Assistance Games (OU-AGs), a formal framework extending assistance games to LLM-based agents. Effective assistance requires reasoning over human preferences that are unbounded, underspecified, and evolving.…
We conduct experiments with algorithmic pricing agents based on Large Language Models (LLMs). In oligopoly settings, LLM-based pricing agents quickly and autonomously reach supracompetitive prices and profits. Variation in seemingly…
Large language models (LLMs) have significant potential to improve operational efficiency in operations management. Deploying these models requires specifying a policy that governs response quality, shapes user experience, and influences…
Task-oriented conversational systems are essential for efficiently addressing diverse user needs, yet their development requires substantial amounts of high-quality conversational data that is challenging and costly to obtain. While large…
Game theory has long served as a foundational tool in cybersecurity to test, predict, and design strategic interactions between attackers and defenders. The recent advent of Large Language Models (LLMs) offers new tools and challenges for…
The language generation and reasoning capabilities of large language models (LLMs) have enabled conversational systems with impressive performance in a variety of tasks, from code generation, to composing essays, to passing STEM and legal…
In this article, we present a new machine learning model by imitation based on the linguistic description of complex phenomena. The idea consists of, first, capturing the behaviour of human players by creating a computational perception…
The future of conversational agents will provide users with personalized information responses. However, a significant challenge in developing models is the lack of large-scale dialogue datasets that span multiple sessions and reflect…
Stated preference (SP) surveys are a key method to research how individuals make trade-offs in hypothetical, also futuristic, scenarios. In energy context this includes key decarbonisation enablement contexts, such as low-carbon…
As large language models (LLMs) demonstrate increasingly advanced capabilities, aligning their behaviors with human values and preferences becomes crucial for their wide adoption. While previous research focuses on general alignment to…