Scholarlink

When answering a user query with relevant entities from a knowledge base (KB), utilizing their semantic class or type information typically structured in the KB is known to improve the retrieval performance for these entities. Accordingly, it is important to identify the target types of entities expected by a query. This work addresses the task of Target Type Identification (TTI) by replacing the established supervisedly learnt ranking approach with a generative approach powered by Large Language Models (LLMs). Beyond assessing the ability of LLMs at predicting query target types, we study aspects of the strategy to elicit generation, in particular, the role of example relevant entities in supporting the explanation of mechanisms behind the LLM predictions.

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

Entity Examples for Explainable Query Target Type Identification with LLMs

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Darío Garigliotti

摘要

When answering a user query with relevant entities from a knowledge base (KB), utilizing their semantic class or type information typically structured in the KB is known to improve the retrieval performance for these entities. Accordingly, it is important to identify the target types of entities expected by a query. This work addresses the task of Target Type Identification (TTI) by replacing the established supervisedly learnt ranking approach with a generative approach powered by Large Language Models (LLMs). Beyond assessing the ability of LLMs at predicting query target types, we study aspects of the strategy to elicit generation, in particular, the role of example relevant entities in supporting the explanation of mechanisms behind the LLM predictions.