Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation
For practitioners of knowledge-intensive QA, this method offers a more controllable and interpretable generation process to reduce hallucinations.
Derivation Prompting reduces unacceptable answers in Retrieval-Augmented Generation for domain-specific QA by using logic-based derivation trees, outperforming traditional RAG and long-context methods.
The application of Large Language Models to Question Answering has shown great promise, but important challenges such as hallucinations and erroneous reasoning arise when using these models, particularly in knowledge-intensive, domain-specific tasks. To address these issues, we introduce Derivation Prompting, a novel prompting technique for the generation step of the Retrieval-Augmented Generation framework. Inspired by logic derivations, this method involves deriving conclusions from initial hypotheses through the systematic application of predefined rules. It constructs a derivation tree that is interpretable and adds control over the generation process. We applied this method in a specific case study, significantly reducing unacceptable answers compared to traditional RAG and long-context window methods.