It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Shaier, Sagi, Hunter, Lawrence E, von der Wense, Katharina
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916458847535104
author Shaier, Sagi
Hunter, Lawrence E
von der Wense, Katharina
author_facet Shaier, Sagi
Hunter, Lawrence E
von der Wense, Katharina
contents Natural language processing has seen rapid progress over the past decade. Due to the speed of developments, some practices get established without proper evaluation. Considering one such case and focusing on reading comprehension, we ask our first research question: 1) How does the order of inputs -- i.e., question and context -- affect model performance? Additionally, given recent advancements in input emphasis, we ask a second research question: 2) Does emphasizing either the question, the context, or both enhance performance? Experimenting with 9 large language models across 3 datasets, we find that presenting the context before the question improves model performance, with an accuracy increase of up to $31\%$. Furthermore, emphasizing the context yields superior results compared to question emphasis, and in general, emphasizing parts of the input is particularly effective for addressing questions that models lack the parametric knowledge to answer. Experimenting with both prompt-based and attention-based emphasis methods, we additionally find that the best method is surprisingly simple: it only requires concatenating a few tokens to the input and results in an accuracy improvement of up to $36\%$, allowing smaller models to outperform their significantly larger counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16779
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension
Shaier, Sagi
Hunter, Lawrence E
von der Wense, Katharina
Computation and Language
Natural language processing has seen rapid progress over the past decade. Due to the speed of developments, some practices get established without proper evaluation. Considering one such case and focusing on reading comprehension, we ask our first research question: 1) How does the order of inputs -- i.e., question and context -- affect model performance? Additionally, given recent advancements in input emphasis, we ask a second research question: 2) Does emphasizing either the question, the context, or both enhance performance? Experimenting with 9 large language models across 3 datasets, we find that presenting the context before the question improves model performance, with an accuracy increase of up to $31\%$. Furthermore, emphasizing the context yields superior results compared to question emphasis, and in general, emphasizing parts of the input is particularly effective for addressing questions that models lack the parametric knowledge to answer. Experimenting with both prompt-based and attention-based emphasis methods, we additionally find that the best method is surprisingly simple: it only requires concatenating a few tokens to the input and results in an accuracy improvement of up to $36\%$, allowing smaller models to outperform their significantly larger counterparts.
title It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension
topic Computation and Language
url https://arxiv.org/abs/2406.16779