Interpretable Question Answering with Knowledge Graphs

TL;DR

This paper introduces an interpretable question answering system that relies solely on knowledge graph retrieval and paraphrasing, avoiding large language models for generation, and demonstrates competitive accuracy on the CRAG benchmark.

Contribution

The work presents a novel pipeline combining knowledge graph querying with paraphrasing, providing an interpretable alternative to LLM-based QA systems.

Findings

Achieved 71.9% accuracy with LLAMA-3.2 on CRAG benchmark.

Achieved 54.4% accuracy with GPT-3.5-Turbo on CRAG benchmark.

Demonstrated effectiveness of knowledge graph-based QA without RAG.

Abstract

This paper presents a question answering system that operates exclusively on a knowledge graph retrieval without relying on retrieval augmented generation (RAG) with large language models (LLMs). Instead, a small paraphraser model is used to paraphrase the entity relationship edges retrieved from querying the knowledge graph. The proposed pipeline is divided into two main stages. The first stage involves pre-processing a document to generate sets of question-answer (QA) pairs. The second stage converts these QAs into a knowledge graph from which graph-based retrieval is performed using embeddings and fuzzy techniques. The graph is queried, re-ranked, and paraphrased to generate a final answer. This work includes an evaluation using LLM-as-a-judge on the CRAG benchmark, which resulted in accuracies of 71.9% and 54.4% using LLAMA-3.2 and GPT-3.5-Turbo, respectively.