In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is important to understand how these models perform such reinforcement learning (RL) tasks and the extent to which they are susceptible to biases. Motivated by the fact that, in humans, it has been widely documented that the value of an outcome depends on how it compares to other local outcomes, the present study focuses on whether similar value encoding biases apply to how LLMs encode rewarding outcomes. Results from experiments with multiple bandit tasks and models show that LLMs exhibit behavioral signatures of a relative value bias. Adding explicit outcome comparisons to the prompt produces opposing effects on performance, enhancing maximization in trained choice sets but impairing generalization to new choice sets. Computational cognitive modeling reveals that LLM behavior is well-described by a simple RL algorithm that incorporates relative values at the outcome encoding stage. Lastly, we present preliminary evidence that the observed biases are not limited to fine-tuned LLMs, and that relative value processing is detectable in the final hidden layer activations of a raw, pretrained model. These findings have important implications for the use of LLMs in decision-making applications.

Algorithmic predictions are increasingly used to inform the allocations of goods and interventions in the public sphere. In these domains, predictions serve as a means to an end. They provide stakeholders with insights into likelihood of future events as a means to improve decision making quality, and enhance social welfare. However, if maximizing welfare is the ultimate goal, prediction is only a small piece of the puzzle. There are various other policy levers a social planner might pursue in order to improve bottom-line outcomes, such as expanding access to available goods, or increasing the effect sizes of interventions. Given this broad range of design decisions, a basic question to ask is: What is the relative value of prediction in algorithmic decision making? How do the improvements in welfare arising from better predictions compare to those of other policy levers? The goal of our work is to initiate the formal study of these questions. Our main results are theoretical in nature. We identify simple, sharp conditions determining the relative value of prediction vis-\`a-vis expanding access, within several statistical models that are popular amongst quantitative social scientists. Furthermore, we illustrate how these theoretical insights may be used to guide the design of algorithmic decision making systems in practice.

As cell phones have grown increasingly prevalent worldwide, with a projected global penetration level of 73 percent in 2020, research on wealth forecasting from digital trail data has concentrated on mobile phone metadata (GSMA, 2017). Machine learning algorithms based on call detail records (CDR) have recently been proved to yield meaningful estimations of prosperity and well-being at a fine geographical resolution. Machine Learning and Artificial Intelligence can be used to target poor populations effectively for humanitarian aid using digital indicators. The challenge of assessing who is qualified for humanitarian help and who is not is a key cause of problems in anti-poverty programme management. Typically, programmes target people based on administrative records like tax records or survey-based asset or consumption measurements.

The general goal of this workshop was to bring t.ogether researchers working toward developing a theoretical framework for the analysis and design of neural networks. The t.echnical focus of the workshop was to address recent. The primary topics addressed the following three areas: 1) Computational complexity issues in neural networks, 2) Complexity issues in learning, and 3) Convergence and numerical properties of learning algorit.hms. Such st.udies, in t.urn, have generated considerable research interest. A similar development can be observed in t.he area of learning as well: Techniques primarily developed in the classical theory of learning are being applied to understand t.he generalization and learning characteristics of neural networks.

The general goal of this workshop was to bring t.ogether researchers working toward developing a theoretical framework for the analysis and design of neural networks. The t.echnical focus of the workshop was to address recent. The primary topics addressed the following three areas: 1) Computational complexity issues in neural networks, 2) Complexity issues in learning, and 3) Convergence and numerical properties of learning algorit.hms. Such st.udies, in t.urn, have generated considerable research interest. A similar development can be observed in t.he area of learning as well: Techniques primarily developed in the classical theory of learning are being applied to understand t.he generalization and learning characteristics of neural networks.

The general goal of this workshop was to bring t.ogether researchers working toward developing a theoretical framework for the analysis and design of neural networks. The t.echnical focus of the workshop was to address recent. The primary topics addressed the following three areas: 1) Computational complexityissues in neural networks, 2) Complexity issues in learning, and 3) Convergence and numerical properties of learning algorit.hms. Such st.udies, in t.urn, have generated considerable research interest. A similar development can be observed in t.he area of learning as well: Techniques primarily developed in the classical theory of learning are being applied to understand t.he generalization and learning characteristics of neural networks.