Infusing Prompts with Syntax and Semantics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Labate, Anton Bulle, Cozman, Fabio Gagliardi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913602306310144
author Labate, Anton Bulle
Cozman, Fabio Gagliardi
author_facet Labate, Anton Bulle
Cozman, Fabio Gagliardi
contents Despite impressive success, language models often generate outputs with flawed linguistic structure. We analyze the effect of directly infusing various kinds of syntactic and semantic information into large language models. To demonstrate the value of our proposals, we focus on the translation of natural language queries to SQL, in particular dealing with languages with less resources than English, to better investigate how much help we can get from low cost syntactic and semantic information. We show that linguistic analysis can significantly boost language models, to the point that we have surpassed previous best systems.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06107
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Infusing Prompts with Syntax and Semantics
Labate, Anton Bulle
Cozman, Fabio Gagliardi
Computation and Language
Despite impressive success, language models often generate outputs with flawed linguistic structure. We analyze the effect of directly infusing various kinds of syntactic and semantic information into large language models. To demonstrate the value of our proposals, we focus on the translation of natural language queries to SQL, in particular dealing with languages with less resources than English, to better investigate how much help we can get from low cost syntactic and semantic information. We show that linguistic analysis can significantly boost language models, to the point that we have surpassed previous best systems.
title Infusing Prompts with Syntax and Semantics
topic Computation and Language
url https://arxiv.org/abs/2412.06107