9 papers
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…
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…
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…
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…
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…
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…