Interpretable Question Answering with Knowledge Graphs
It addresses interpretable QA for users needing transparent systems, but is incremental as it adapts existing graph methods to avoid RAG.
The paper tackles question answering by using a knowledge graph retrieval system without large language models, achieving accuracies of 71.9% and 54.4% on the CRAG benchmark with LLAMA-3.2 and GPT-3.5-Turbo as judges.
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.