Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs
By: Alberto Cattaneo, Carlo Luschi, Daniel Justus
Potential Business Impact:
Makes AI smarter by teaching it to find facts.
Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various solutions have been proposed, a comparison of methods is difficult due to the lack of challenging QA datasets with ground-truth targets for graph retrieval. We present SynthKGQA, a framework for generating high-quality synthetic Knowledge Graph Question Answering datasets from any Knowledge Graph, providing the full set of ground-truth facts in the KG to reason over each question. We show how, in addition to enabling more informative benchmarking of KG retrievers, the data produced with SynthKGQA also allows us to train better models. We apply SynthKGQA to Wikidata to generate GTSQA, a new dataset designed to test zero-shot generalization abilities of KG retrievers with respect to unseen graph structures and relation types, and benchmark popular solutions for KG-augmented LLMs on it.
Similar Papers
Knowledge Graph-extended Retrieval Augmented Generation for Question Answering
Machine Learning (CS)
AI answers questions better by using facts.
Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
Computation and Language
Makes AI answers more truthful by building knowledge maps.
KGQuest: Template-Driven QA Generation from Knowledge Graphs with LLM-Based Refinement
Computation and Language
Creates smart questions and answers from facts.