Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation
This addresses the need for scalable knowledge integration in LLMs for domains like medicine, though it is incremental as it builds on existing fine-tuning and adapter techniques.
The paper tackles the problem of enabling large language models to use up-to-date or domain-specific knowledge for dialogue generation by introducing KEDiT, an efficient fine-tuning method that updates less than 2% of parameters and outperforms baselines on datasets like Wizard of Wikipedia and PubMed-Dialog in automatic, LLM-based, and human evaluations.
Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data. To address this gap, we introduce KEDiT, an efficient method for fine-tuning LLMs for knowledge-grounded dialogue generation. KEDiT operates in two main phases: first, it employs an information bottleneck to compress retrieved knowledge into learnable parameters, retaining essential information while minimizing computational overhead. Second, a lightweight knowledge-aware adapter integrates these compressed knowledge vectors into the LLM during fine-tuning, updating less than 2\% of the model parameters. The experimental results on the Wizard of Wikipedia and a newly constructed PubMed-Dialog dataset demonstrate that KEDiT excels in generating contextually relevant and informative responses, outperforming competitive baselines in automatic, LLM-based, and human evaluations. This approach effectively combines the strengths of pretrained LLMs with the adaptability needed for incorporating dynamic knowledge, presenting a scalable solution for fields such as medicine.