activity
20242026
collaborators

9 papers

econ.EM2026

Partial Identification from LLM Prompts

Xiaohong Chen, Ashesh Rambachan, Elie Tamer

Large language models are increasingly used as binary classifiers when the true label is latent. We study partial identification of the prevalence from panels of L…

econ.EM2026

Program Evaluation with Remotely Sensed Outcomes

Ashesh Rambachan, Rahul Singh, Davide Viviano

We study causal inference in experiments and quasi-experiments, where the economic outcome is imperfectly measured by a remotely sensed variable. The remotely sensed variable is lo…

cs.LG2025

What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models

Keyon Vafa, Peter G. Chang, Ashesh Rambachan +1

Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the…

econ.EM2025

Large Language Models: An Applied Econometric Framework

Jens Ludwig, Sendhil Mullainathan, Ashesh Rambachan

Large language models (LLMs) enable researchers to analyze text at unprecedented scale and minimal cost. Researchers can now revisit old questions and tackle novel ones with rich d…

econ.EM2025

Robust Design and Evaluation of Predictive Algorithms under Unobserved Confounding

Ashesh Rambachan, Amanda Coston, Edward Kennedy

Predictive algorithms inform consequential decisions in settings with selective labels: outcomes are observed only for units selected by past decision makers. This creates an ident…

econ.EM2025

From Predictive Algorithms to Automatic Generation of Anomalies

Sendhil Mullainathan, Ashesh Rambachan

How can we extract theoretical insights from machine learning algorithms? We take a familiar lesson: researchers often turn their intuitions into theoretical insights by constructi…