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.- Anthology ID:
- 2023.findings-emnlp.675
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10071–10081
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.675
- DOI:
- 10.18653/v1/2023.findings-emnlp.675
- Cite (ACL):
- Qinyu Chen, Wenhao Wu, and Sujian Li. 2023. Exploring In-Context Learning for Knowledge Grounded Dialog Generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10071–10081, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Exploring In-Context Learning for Knowledge Grounded Dialog Generation (Chen et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/fix-volume-bibkeys/2023.findings-emnlp.675.pdf