As a primary means of information acquisition, information retrieval (IR) systems, such as
search engines, have integrated themselves into our daily lives. These systems also serve …

Decoder-only large language model (LLM)-based embedding models are beginning to
outperform BERT or T5-based embedding models in general-purpose text embedding tasks …

We propose a novel zero-shot document ranking approach based on Large Language
Models (LLMs): the Setwise prompting approach. Our approach complements existing …

A major challenge facing the world is the provision of equitable and universal access to
quality education. Recent advances in generative AI (gen AI) have created excitement about …

Abstract We introduce the Block Transformer which adopts hierarchical global-to-local
modeling to autoregressive transformers to mitigate the inference bottlenecks associated …

We present systematic efforts in building long-context multilingual text representation model
(TRM) and reranker from scratch for text retrieval. We first introduce a text encoder (base …

Text embedding methods have become increasingly popular in both industrial and
academic fields due to their critical role in a variety of natural language processing tasks …

Utilizing large language models (LLMs) for zero-shot document ranking is done in one of
two ways:(1) prompt-based re-ranking methods, which require no further training but are …

Long-context language models (LCLMs) have the potential to revolutionize our approach to
tasks traditionally reliant on external tools like retrieval systems or databases. Leveraging …

Existing retrieval benchmarks primarily consist of information-seeking queries (eg,
aggregated questions from search engines) where keyword or semantic-based retrieval is …