Principles from Clinical Research for NLP Model Generalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Elangovan, Aparna, He, Jiayuan, Li, Yuan, Verspoor, Karin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916188221603840
author Elangovan, Aparna
He, Jiayuan
Li, Yuan
Verspoor, Karin
author_facet Elangovan, Aparna
He, Jiayuan
Li, Yuan
Verspoor, Karin
contents The NLP community typically relies on performance of a model on a held-out test set to assess generalization. Performance drops observed in datasets outside of official test sets are generally attributed to "out-of-distribution" effects. Here, we explore the foundations of generalizability and study the factors that affect it, articulating lessons from clinical studies. In clinical research, generalizability is an act of reasoning that depends on (a) internal validity of experiments to ensure controlled measurement of cause and effect, and (b) external validity or transportability of the results to the wider population. We demonstrate how learning spurious correlations, such as the distance between entities in relation extraction tasks, can affect a model's internal validity and in turn adversely impact generalization. We, therefore, present the need to ensure internal validity when building machine learning models in NLP. Our recommendations also apply to generative large language models, as they are known to be sensitive to even minor semantic preserving alterations. We also propose adapting the idea of matching in randomized controlled trials and observational studies to NLP evaluation to measure causation.
format Preprint
id arxiv_https___arxiv_org_abs_2311_03663
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Principles from Clinical Research for NLP Model Generalization
Elangovan, Aparna
He, Jiayuan
Li, Yuan
Verspoor, Karin
Computation and Language
The NLP community typically relies on performance of a model on a held-out test set to assess generalization. Performance drops observed in datasets outside of official test sets are generally attributed to "out-of-distribution" effects. Here, we explore the foundations of generalizability and study the factors that affect it, articulating lessons from clinical studies. In clinical research, generalizability is an act of reasoning that depends on (a) internal validity of experiments to ensure controlled measurement of cause and effect, and (b) external validity or transportability of the results to the wider population. We demonstrate how learning spurious correlations, such as the distance between entities in relation extraction tasks, can affect a model's internal validity and in turn adversely impact generalization. We, therefore, present the need to ensure internal validity when building machine learning models in NLP. Our recommendations also apply to generative large language models, as they are known to be sensitive to even minor semantic preserving alterations. We also propose adapting the idea of matching in randomized controlled trials and observational studies to NLP evaluation to measure causation.
title Principles from Clinical Research for NLP Model Generalization
topic Computation and Language
url https://arxiv.org/abs/2311.03663