Exploring In-Context Learning for Knowledge Grounded Dialog Generation
Qinyu Chen, Wenhao Wu, Sujian Li
Abstract
Large neural-based dialog generation models have been applied in many real-life scenarios, yet they are prone to hallucination and tend to produce factually inaccurate outputs which raise great concerns. To alleviate this problem, we propose a plug-and-play retrieval-based framework IKA, which leverages in-context learning and retrieval techniques to enhance LLMs on knowledge grounded dialog generation. We design thorough experiments on a large-scale knowledge graph with 1M+ facts to investigate the effectiveness and generalization of our framework. Experiments show that our method surpasses previous training-based SOTA by a large margin, specifically 46.67% in BLEU4, 26.01% in ROUGE-L, 122.90% in BARTScore and 30.50% in Entity Coverage F1. Further analysis show promising abilities of LLMs to perform knowledge-intensive tasks, which is previously considered weak and understudied.
BibTeX
@inproceedings{
chen2023exploring,
title={Exploring In-Context Learning for Knowledge Grounded Dialog Generation},
author={Qinyu Chen and Wenhao Wu and Sujian Li},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=NbkVQsbaqJ}
}