The rise of large language models (LLMs) had a transformative impact on
...
Traditionally, sparse retrieval systems relied on lexical representation...
BEIR is a benchmark dataset for zero-shot evaluation of information retr...
The ever-increasing size of language models curtails their widespread ac...
The advent of multilingual language models has generated a resurgence of...
Dense retrievers encode documents into fixed dimensional embeddings. How...
Dense retrieval approaches can overcome the lexical gap and lead to
sign...
Neural IR models have often been studied in homogeneous and narrow setti...
There are two approaches for pairwise sentence scoring: Cross-encoders, ...