paper-with-me

홈 › Papers

Assessing Generalization for Subpopulation Representative Modeling via In-Context Learning

2024-02-12 · Gabriel Simmons, Vladislav Savinov

This study evaluates the ability of Large Language Model (LLM)-based Subpopulation Representative Models (SRMs) to generalize from empirical data, utilizing in-context learning with data from the 2016 and 2020 American National Election Studies. We explore generalization across response variables and demographic subgroups. While conditioning with empirical data improves performance on the whole, the benefit of in-context learning varies considerably across demographics, sometimes hurting performance for one demographic while helping performance for others. The inequitable benefits of in-context learning for SRM present a challenge for practitioners implementing SRMs, and for decision-makers who might come to rely on them. Our work highlights a need for fine-grained benchmarks captured from diverse subpopulations that test not only fidelity but generalization.

📄 PDF Abstract BibTeX arXiv:2402.07368

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

American 설명 없음
SRM SRM combines style transfer with an attention mechanism. Its main contribution is style pooling which utilizes both mean and standard deviation of the input features to improve…

Similar Papers 제목 키워드 기반

Cadre Modeling: Simultaneously Discovering Subpopulations and Predictive Models

2018-02-07 · Alexander New, Curt Breneman, Kristin P. Bennett

We consider the problem in regression analysis of identifying subpopulations that exhibit different patterns of response, where each subpopulation requires a different underlying model. Unlike statistical cohorts, these …

Clusteringfeature selectionPredictionregression

Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data

2021-03-05 · Esther Rolf, Theodora Worledge, Benjamin Recht, Michael I. Jordan

Collecting more diverse and representative training data is often touted as a remedy for the disparate performance of machine learning predictors across subpopulations. However, a precise framework for understanding how …

Diversity

BREEDS: Benchmarks for Subpopulation Shift

2020-08-11 · ICLR 2021 1 · Shibani Santurkar, Dimitris Tsipras, Aleksander Madry

We develop a methodology for assessing the robustness of models to subpopulation shift---specifically, their ability to generalize to novel data subpopulations that were not observed during training. Our approach leverag…

Unsupervised Recalibration

2019-08-24 · Albert Ziegler, Paweł Czyż

Unsupervised recalibration (URC) is a general way to improve the accuracy of an already trained probabilistic classification or regression model upon encountering new data while deployed in the field. URC does not requir…

Assessing External Validity Over Worst-case Subpopulations

2020-07-05 · Sookyo Jeong, Hongseok Namkoong

Study populations are typically sampled from limited points in space and time, and marginalized groups are underrepresented. To assess the external validity of randomized and observational studies, we propose and evaluat…

Causal Inferencevalid