Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916236109021184 |
|---|---|
| author | Xu, Zhentao Cruz, Mark Jerome Guevara, Matthew Wang, Tie Deshpande, Manasi Wang, Xiaofeng Li, Zheng |
| author_facet | Xu, Zhentao Cruz, Mark Jerome Guevara, Matthew Wang, Tie Deshpande, Manasi Wang, Xiaofeng Li, Zheng |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17723 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering Xu, Zhentao Cruz, Mark Jerome Guevara, Matthew Wang, Tie Deshpande, Manasi Wang, Xiaofeng Li, Zheng Information Retrieval Artificial Intelligence Computation and Language Machine Learning I.2 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%. |
| title | Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering |
| topic | Information Retrieval Artificial Intelligence Computation and Language Machine Learning I.2 |
| url | https://arxiv.org/abs/2404.17723 |