Related papers: From Outcome-Based to Language-Based Preferences
Large language models have been extensively studied for emotion recognition and moral reasoning as distinct capabilities, yet the extent to which emotions influence moral judgment remains underexplored. In this work, we develop an…
Game theory provides a quantitative framework for analyzing the behavior of rational agents. The Iterated Prisoner's Dilemma in particular has become a standard model for studying cooperation and cheating, with cooperation often emerging as…
Math is constructed by people for people: just as natural language corpora reflect not just propositions but the communicative goals of language users, the math data that models are trained on reflects not just idealized mathematical…
Robots need models of human behavior for both inferring human goals and preferences, and predicting what people will do. A common model is the Boltzmann noisily-rational decision model, which assumes people approximately optimize a reward…
We explore a new mechanism to explain polarization phenomena in opinion dynamics in which agents evaluate alternative views on the basis of the social feedback obtained on expressing them. High support of the favored opinion in the social…
Learning from human feedback has gained traction in fields like robotics and natural language processing in recent years. While prior works mostly rely on human feedback in the form of comparisons, language is a preferable modality that…
Regression plays a key role in many research areas and its variable selection is a classic and major problem. This study emphasizes cost of predictors to be purchased for future use, when we select a subset of them. Its economic aspect is…
Iterated reference games - in which players repeatedly pick out novel referents using language - present a test case for agents' ability to perform context-sensitive pragmatic reasoning in multi-turn linguistic environments. We tested…
Language models (LMs) tend to show human-like preferences on a number of syntactic phenomena, but the extent to which these are attributable to direct exposure to the phenomena or more general properties of language is unclear. We explore…
In a digital age where companies face rapid changes in technology, consumer trends, and business environments, there is a critical need for continual revision of the business model in response to disruptive innovation. A pillar of…
In order for AI systems to communicate effectively with people, they must understand how we make decisions. However, people's decisions are not always rational, so the implicit internal models of human decision-making in Large Language…
As large language models (LLMs) increasingly participate in high-stakes decision-making, a central societal debate has revolved around which moral frameworks-deontological or utilitarian-should guide machine behavior. However, a largely…
Human interactions are influenced by emotions, temperament, and affection, often conflicting with individuals' underlying preferences. Without explicit knowledge of those preferences, judging whether behaviour is appropriate becomes…
Large language models implicitly encode preferences over human values, yet steering them often requires large training data. In this work, we investigate a simple approach: Can we reliably modify a model's value system in downstream…
Cooperation is of utmost importance to society as a whole, but is often challenged by individual self-interests. While game theory has studied this problem extensively, there is little work on interactions within and across groups with…
The psychology of the individual is continuously changing in nature, which has a significant influence on the evolutionary dynamics of populations. To study the influence of the continuously changing psychology of individuals on the…
We study the evolutionary dynamics of games under environmental feedback using replicator equations for two interacting populations. One key feature is to consider jointly the co-evolution of the dynamic payoff matrices and the state of the…
The relationship between the quality of a string, as judged by a human reader, and its probability, $p(\boldsymbol{y})$ under a language model undergirds the development of better language models. For example, many popular algorithms for…
This paper investigates the knowledge of language models from the perspective of Bayesian epistemology. We explore how language models adjust their confidence and responses when presented with evidence with varying levels of informativeness…
Agents that negotiate with humans find broad applications in pedagogy and conversational AI. Most efforts in human-agent negotiations rely on restrictive menu-driven interfaces for communication. To advance the research in language-based…