Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering

TL;DR

This paper presents a novel retrieval-augmented generation approach that integrates knowledge graphs with large language models to improve customer service question answering by better capturing issue structure and relations.

Contribution

It introduces a method that constructs and utilizes a knowledge graph from historical issues to enhance retrieval and answer generation in customer service QA systems.

Findings

Outperforms baseline by 77.6% in MRR

Reduces median resolution time by 28.6%

Improves answer quality metrics like BLEU

Abstract

In customer service technical support, swiftly and accurately retrieving relevant past issues is critical for efficiently resolving customer inquiries. The conventional retrieval methods in retrieval-augmented generation (RAG) for large language models (LLMs) treat a large corpus of past issue tracking tickets as plain text, ignoring the crucial intra-issue structure and inter-issue relations, which limits performance. We introduce a novel customer service question-answering method that amalgamates RAG with a knowledge graph (KG). Our method constructs a KG from historical issues for use in retrieval, retaining the intra-issue structure and inter-issue relations. During the question-answering phase, our method parses consumer queries and retrieves related sub-graphs from the KG to generate answers. This integration of a KG not only improves retrieval accuracy by preserving customer service structure information but also enhances answering quality by mitigating the effects of text segmentation. Empirical assessments on our benchmark datasets, utilizing key retrieval (MRR, Recall@K, NDCG@K) and text generation (BLEU, ROUGE, METEOR) metrics, reveal that our method outperforms the baseline by 77.6% in MRR and by 0.32 in BLEU. Our method has been deployed within LinkedIn's customer service team for approximately six months and has reduced the median per-issue resolution time by 28.6%.