Related papers: PyLate: Flexible Training and Retrieval for Late I…

We study serving retrieval models, specifically late interaction models like ColBERT, to many concurrent users at once and under a small budget, in which the index may not fit in memory. We present ColBERT-serve, a novel serving system that…

While question-like queries are gaining popularity and search engines' users increasingly adopt them, keyphrase search has traditionally been the cornerstone of web search. This query type is also prevalent in specialised search tasks such…

Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrieval often replicate techniques developed for text-only…

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…

State-of-the-art neural retrievers predominantly focus on high-resource languages like English, which impedes their adoption in retrieval scenarios involving other languages. Current approaches circumvent the lack of high-quality labeled…

Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Currently, pre-trained models can be considered the default choice for a wide range of NLP tasks. Despite their SoTA results, there is practical evidence that these models may require a different number of computing layers for different…

High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…

Multi-vector retrieval methods, exemplified by the ColBERT architecture, have shown substantial promise for retrieval by providing strong trade-offs in terms of retrieval latency and effectiveness. However, they come at a high cost in terms…

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized…

Knowledge tracing (KT) is the task of using students' historical learning interaction data to model their knowledge mastery over time so as to make predictions on their future interaction performance. Recently, remarkable progress has been…

Communication protocol design is a central challenge in large language model-based multi-agent systems. Existing single-channel approaches face an inherent communication trilemma: text-based methods are interpretable but verbose, while…

The advent of transformer-based models such as BERT has led to the rise of neural ranking models. These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25. While…

This short paper presents a preliminary analysis of three popular Visual Question Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in the context of answering questions relating to driving scenarios. The performance of these models…

Retrieving relevant evidence from visually rich documents such as textbooks, technical reports, and manuals is challenging due to long context, complex layouts, and weak lexical overlap between user questions and supporting pages. We…

While Late Interaction models exhibit strong retrieval performance, many of their underlying dynamics remain understudied, potentially hiding performance bottlenecks. In this work, we focus on two topics in Late Interaction retrieval: a…

With the widespread of digital environments, reliable authentication and continuous access control has become crucial. It can minimize cyber attacks and prevent frauds, specially those associated with identity theft. A particular interest…

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

Pre-trained Language Models (LMs) have become an integral part of Natural Language Processing (NLP) in recent years, due to their superior performance in downstream applications. In spite of this resounding success, the usability of LMs is…