Infusing Knowledge into Large Language Models with Contextual Prompts
Kinshuk Vasisht, Balaji Ganesan, Vikas Kumar, Vasudha Bhatnagar
Abstract
Knowledge infusion is a promising method for enhancing Large Language Models for domainspecific NLP tasks rather than pre-training models over large data from scratch. These augmented LLMs typically depend on additional pre-training or knowledge prompts from an existing knowledge graph, which is impractical in many applications. In contrast, knowledge infusion directly from relevant documents is more generalisable and alleviates the need for structured knowledge graphs while also being useful for entities that are usually not found in any knowledge graph. With this motivation, we propose a simple yet generalisable approach for knowledge infusion by generating prompts from the context in the input text. Our experiments show the effectiveness of our approach which we evaluate by probing the fine-tuned LLMs.- Anthology ID:
- 2023.icon-1.65
- Volume:
- Proceedings of the 20th International Conference on Natural Language Processing (ICON)
- Month:
- December
- Year:
- 2023
- Address:
- Goa University, Goa, India
- Editors:
- Jyoti D. Pawar, Sobha Lalitha Devi
- Venue:
- ICON
- SIG:
- SIGLEX
- Publisher:
- NLP Association of India (NLPAI)
- Note:
- Pages:
- 657–662
- Language:
- URL:
- https://aclanthology.org/2023.icon-1.65
- DOI:
- Cite (ACL):
- Kinshuk Vasisht, Balaji Ganesan, Vikas Kumar, and Vasudha Bhatnagar. 2023. Infusing Knowledge into Large Language Models with Contextual Prompts. In Proceedings of the 20th International Conference on Natural Language Processing (ICON), pages 657–662, Goa University, Goa, India. NLP Association of India (NLPAI).
- Cite (Informal):
- Infusing Knowledge into Large Language Models with Contextual Prompts (Vasisht et al., ICON 2023)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/2023.icon-1.65.pdf