Tag: Importance Sampling
All the articles with the tag "Importance Sampling".
-
Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models
This paper introduces Direct Retrieval-augmented Optimization (DRO), a framework that synergizes knowledge selection and LLM generation through end-to-end training using a variational approach, achieving 5-15% improvements in EM and F1 scores across five QA datasets.