DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers

By Xueguang Ma, Xi Victoria Lin, Barlas Oğuz, Jimmy Lin, Wen-Tau Yih, Xilun Chen. 2025

Subfields: Information Retrieval & Search, Efficiency & Compression

Citations in the corpus

• IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions (2026, unknown): “We also include decoder models: Stella (Zhang et al., 2025a) and DRAMA (Ma et al., 2025).”
• ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance (2025, unknown): “For instance, methods such as LLM-QL (Zhang et al., 2025) and DRAMA (Ma et al., 2025) pro-pose leveraging LLMs to generate new queries or training triplets for dense retriever optimization.”