SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection

TL;DR

This paper introduces a method to evaluate how training data influences LLM performance in generating SPARQL queries for QA over knowledge graphs, addressing issues of memorization and knowledge injection.

Contribution

It proposes a novel evaluation approach for LLMs in KGQA that isolates training data effects, including knowledge injection, across various conditions.

Findings

Assessing training data influence on LLM performance

Identifying memorization effects in benchmark datasets

Providing a portable, robust evaluation method

Abstract

Nowadays, the importance of software with natural-language user interfaces cannot be underestimated. In particular, in Question Answering (QA) systems, generating a SPARQL query for a given natural-language question (often named Query Building) from the information retrieved from the same question is the central task of QA systems working over Knowledge Graphs (KGQA). Due to the rise of Large Language Models (LLMs), they are considered a well-suited method to increase the quality of the question-answering functionality, as there is still a lot of room for improvement, aiming for enhanced quality and trustworthiness. However, LLMs are trained on web data, where researchers have no control over whether the benchmark or the knowledge graph was already included in the training data. In this paper, we introduce a novel method that evaluates the quality of LLMs by generating a SPARQL query from a natural-language question under various conditions: (1) zero-shot SPARQL generation, (2) with knowledge injection, and (3) with "anonymized" knowledge injection. This enables us, for the first time, to estimate the influence of the training data on the QA quality improved by LLMs. Ultimately, this will help to identify how portable a method is or whether good results might mostly be achieved because a benchmark was already included in the training data (cf. LLM memorization). The developed method is portable, robust, and supports any knowledge graph; therefore, it could be easily applied to any KGQA or LLM, s.t., generating consistent insights into the actual LLM capabilities is possible.