# QirK: Question Answering via Intermediate Representation on Knowledge Graphs

Source: [QirK: Question Answering via Intermediate Representation on Knowledge Graphs](<https://www.sota2.com/research/paper/68fa74831e209131cea6218a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:11:37.234Z

Authors: Jan Luca Scheerer, Anton Lykov, Moe Kayali, Ilias Fountalis, Dan Olteanu, Nikolaos Vasiloglou, Dan Suciu

Published: 2024-08-14T12:19:25.000Z

## Abstract

We demonstrate QirK, a system for answering natural language questions on Knowledge Graphs (KG). QirK can answer structurally complex questions that are still beyond the reach of emerging Large Language Models (LLMs). It does so using a unique combination of database technology, LLMs, and semantic search over vector embeddings. The glue for these components is an intermediate representation (IR). The input question is mapped to IR using LLMs, which is then repaired into a valid relational database query with the aid of a semantic search on vector embeddings. This allows a practical synthesis of LLM capabilities and KG reliability.   A short video demonstrating QirK is available at https://youtu.be/6c81BLmOZ0U.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2408.07494>)

[PDF](<https://arxiv.org/pdf/2408.07494.pdf>)