Add to ORKGBi-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 range of parameter count on both in-domain and out-of-domain scenarios. We find that the number of parameters and early query-document interactions of cross-encoders play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that cross-encoders largely outperform bi-encoders of similar size in several tasks. In the BEIR benchmark, our largest cross-encoder ...
In recent years, large pre-trained transformers have led to substantial gains in performance over tr...
Multi-vector retrieval models improve over single-vector dual encoders on many information retrieval...
Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved ...
Recent work has shown that small distilled language models are strong competitors to models that are...
Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased...
Query expansion has been proved to be effective in improving recall and precision of first-stage ret...
In this work, we propose a simple method that applies a large language model (LLM) to large-scale re...
Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transfor...
Current state-of-the-art approaches to cross- modal retrieval process text and visual input jointly,...
Current dense text retrieval models face two typical challenges. First, they adopt a siamese dual-en...
State-of-the-art neural (re)rankers are notoriously data hungry which - given the lack of large-scal...
The advent of contextualised language models has brought gains in search effectiveness, not just whe...
The Coronavirus (COVID-19) pandemic has led to a rapidly growing 'infodemic' of health information o...
Learning to search is the task of building artificial agents that learn to autonomously use a search...
Humans can perform unseen tasks by recalling relevant skills acquired previously and then generalizi...
In recent years, large pre-trained transformers have led to substantial gains in performance over tr...
Multi-vector retrieval models improve over single-vector dual encoders on many information retrieval...
Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved ...
Recent work has shown that small distilled language models are strong competitors to models that are...
Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased...
Query expansion has been proved to be effective in improving recall and precision of first-stage ret...
In this work, we propose a simple method that applies a large language model (LLM) to large-scale re...
Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transfor...
Current state-of-the-art approaches to cross- modal retrieval process text and visual input jointly,...
Current dense text retrieval models face two typical challenges. First, they adopt a siamese dual-en...
State-of-the-art neural (re)rankers are notoriously data hungry which - given the lack of large-scal...
The advent of contextualised language models has brought gains in search effectiveness, not just whe...
The Coronavirus (COVID-19) pandemic has led to a rapidly growing 'infodemic' of health information o...
Learning to search is the task of building artificial agents that learn to autonomously use a search...
Humans can perform unseen tasks by recalling relevant skills acquired previously and then generalizi...
In recent years, large pre-trained transformers have led to substantial gains in performance over tr...
Multi-vector retrieval models improve over single-vector dual encoders on many information retrieval...
Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved ...