Open manisnesan opened 1 year ago
UDAPDR - Unsupervised Domain Adaptation via LLM Prompting and Distillation for Rerankers
Related Demonstrate Search Predict architecture , Promptagator++
An extension of the blogpost Jo Kristian Bergum - Boosting Ranking performance using minimal supervision - YouTube
Sujitpal also showcased this idea in haystack US 2023 talk
https://github.com/manisnesan/til/issues/41#issuecomment-1575046998
Smaller Open Source LLMs for Query Expansion
smaller variants of T5 and UL2 outperform BM25 on datasets like BEIR.
Even in zero-shot settings.
UL2's Recall@1K on BEIR: • 72.43 for BM25 • 74.47 for Query2Doc • 72.86 for Query2Expansion • 75.07 for Chain of Thought
Improved text ranking with few shot prompting