Related papers: From Outcome-Based to Language-Based Preferences
Kinetic exchange models have been successful in explaining the shape of the income/wealth distribution in the economies. However, such models usually make some ad-hoc assumptions when it comes to determining the savings factor. Here, we…
Human-robot interaction exerts influence towards the human, which often changes behavior. This article explores an externality of this changed behavior - preference change. It expands on previous work on preference change in AI systems.…
Preferences often change -- even in short time intervals -- due to either the mere passage of time (present-biased preferences) or changes in environmental conditions (state-dependent preferences). On the basis of the empirical findings in…
Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and empathy, and values, such as helpfulness, harmlessness, and honesty. This is done to…
I consider decision-making constrained by considerations of morality, rationality, or other virtues. The decision maker (DM) has a true preference over outcomes, but feels compelled to choose among outcomes that are top-ranked by some…
This study identifies the specific conditions under which large language models exhibit human-like gambling addiction patterns, providing critical insights into their decision-making mechanisms and AI safety. We analyze LLM decision-making…
Modeling the preferences of agents over a set of alternatives is a principal concern in many areas. The dominant approach has been to find a single reward/utility function with the property that alternatives yielding higher rewards are…
We study sequential language games in which two players, each with private information, communicate to achieve a common goal. In such games, a successful player must (i) infer the partner's private information from the partner's messages,…
As large language models (LLMs) increasingly act as autonomous agents in markets and organizations, their behavior in strategic environments becomes economically consequential. We document that off-the-shelf LLM agents exhibit systematic…
In repeated games, such as auctions, players rely on autonomous learning agents to choose their actions. We study settings in which players have their agents make monetary transfers to other agents during play at their own expense, in order…
Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs' behavior in various tasks. In this paper, we provide a…
The recent proliferation of research into transformer based natural language processing has led to a number of studies which attempt to detect the presence of human-like cognitive behavior in the models. We contend that, as is true of human…
Traditional linguistic theories have largely regard language as a formal system composed of rigid rules. However, their failures in processing real language, the recent successes in statistical natural language processing, and the findings…
As large language models (LLMs) enter the mainstream, aligning them to foster constructive dialogue rather than exacerbate societal divisions is critical. Using an individualized and multicultural alignment dataset of over 7,500…
Getting a group to adopt cooperative norms is an enduring challenge. But in real-world settings, individuals don't just passively accept static environments, they act both within and upon the social systems that structure their…
In repeated interactions between individuals, we do not expect that exactly the same situation will occur from one time to another. Contrary to what is common in models of repeated games in the literature, most real situations may differ a…
It is well known that reinforcement learning can be cast as inference in an appropriate probabilistic model. However, this commonly involves introducing a distribution over agent trajectories with probabilities proportional to exponentiated…
I revisit the standard moral-hazard model, in which an agent's preference over contracts is rooted in costly effort choice. I characterise the behavioural content of the model in terms of empirically testable axioms, and show that the…
Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior. However, in cases related to safety, without precise instructions to human…
We examine a naming game on an adaptive weighted network. A weight of connection for a given pair of agents depends on their communication success rate and determines the probability with which the agents communicate. In some cases,…