Recent work has shown that incorporating explanations into the output generated by large
language models (LLMs) can significantly enhance performance on a broad spectrum of …

Recent work has shown that small distilled language models are strong competitors to
models that are orders of magnitude larger and slower in a wide range of information …

Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines.
In this work we study the generalization ability of these two types of architectures on a wide …

Recent work has shown that inducing a large language model (LLM) to generate
explanations prior to outputting an answer is an effective strategy to improve performance on …

MMEAD, or MS MARCO Entity Annotations and Disambiguations, is a resource for entity
links for the MS MARCO datasets. We specify a format to store and share links for both …

Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid
retrievers leverage indexing-heavy dense retrievers. In this work, we study" Is it possible to …

Abstract The latest Dense Retrieval (DR) models typically encode queries and documents
using BERT and subsequently apply a cosine similarity-based scoring to determine the …

Document expansion is a technique that aims to reduce the likelihood of term mismatch by
augmenting documents with related terms or queries. Doc2Query minus minus (Doc2Query …

Neural ranking (NR) has become a key component for open-domain question-answering in
order to access external knowledge. However, training a good NR model requires …

Dense indexes derived from whole-of-document neural models are now more effective at
locating likely-relevant documents than are conventional term-based inverted indexes. That …