Scholarlink

<p>Despite impressive success, Large Language Models (LLMs) sometimes generate outputs with flawed linguistic structure. We analyze the effect of directly infusing syntactic and semantic information into LLMs. 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 and even surpass existing best systems for some languages.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Infusing Syntax and Semantics into LLMs

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月17日

查看全文
  • Anton Bulle Labate,
  • Fabio Gagliardi Cozman

摘要

Despite impressive success, Large Language Models (LLMs) sometimes generate outputs with flawed linguistic structure. We analyze the effect of directly infusing syntactic and semantic information into LLMs. 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 and even surpass existing best systems for some languages.