Research

Large language models (LLMs) have demonstrated promise in emulating human-like responses across a wide range of tasks. In this paper, we propose a novel alignment framework that treats LLMs as agent proxies for human survey respondents, affording a cost-effective and steerable solution to two pressing challenges in the social sciences: the rising cost of survey deployment and the growing demographic imbalance in survey response data. Drawing inspiration from the theory of revealed preference, we formulate alignment as a two-stage problem: constructing diverse agent personas called endowments that simulate plausible respondent profiles, and selecting a representative subset to approximate a ground-truth population based on observed data. To implement the paradigm, we introduce P2P, a system that steers LLM agents toward representative behavioral patterns using structured prompt engineering, entropy-based sampling, and regression-based selection. Unlike personalization-heavy approaches, our alignment approach is demographic-agnostic and relies only on aggregate survey results, offering better generalizability and parsimony. Beyond improving data efficiency in social science research, our framework offers a testbed for studying the operationalization of pluralistic alignment. We demonstrate the efficacy of our approach on real-world opinion survey datasets, showing that our aligned agent populations can reproduce aggregate response patterns with high fidelity and exhibit substantial response diversity, even without demographic conditioning.

Collaborative machine learning (CML) provides a promising paradigm for democratizing advanced technologies by enabling cost-sharing among participants. However, the potential for rent-seeking behaviors among parties can undermine such collaborations. Contract theory presents a viable solution by rewarding participants with models of varying accuracy based on their contributions. However, unlike monetary compensation, using models as rewards introduces unique challenges, particularly due to the stochastic nature of these rewards when contribution costs are privately held information. This paper formalizes the optimal contracting problem within CML and proposes a transformation that simplifies the non-convex optimization problem into one that can be solved through convex optimization algorithms. We conduct a detailed analysis of the properties that an optimal contract must satisfy when models serve as the rewards, and we explore the potential benefits and welfare implications of these contract-driven CML schemes through numerical experiments.

Parameter non-constancy has been a prevalent issue in empirical economic research. The advent of a new technology, the implementation of an intervention policy or the unexpected event of a global pandemic could all result in shifts to the parameters of a time series model. Traditionally, detection of parameter shifts is done as part of the diagnostic tests after a model has been selected and estimated. Yet, this approach has many drawbacks, including, inter alia, a high labour cost in the subsequent modelling of the parameter non-constancy. As an alternative, this essay provides an analysis of multiplicative-indicator saturation (MIS), which is designed to capture parameter shifts during the model selection process. Theoretical analysis of the method is done with a splif-half selection algorithm pioneered by Hendry et al. (2008). Monte Carlo simulations are conducted to evaluate the performance of MIS in a multi-path block search algorithm with different settings, followed by a comparison with other well-established saturation methods. The essay also introduces a variant of MIS called Parsimonious MIS, which has improved performance in a partial change model where parameter shifts happen to one of the regressors. Based on the analysis, ideas on future research are suggested.