Related papers: Interpretable & Time-Budget-Constrained Contextual…

Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce…

Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized…

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We…

Recent Transformer-based summarization models have provided a promising approach to abstractive summarization. They go beyond sentence selection and extractive strategies to deal with more complicated tasks such as novel word generation and…

The performance of a cross-sectional currency strategy depends crucially on accurately ranking instruments prior to portfolio construction. While this ranking step is traditionally performed using heuristics, or by sorting the outputs…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for…

We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. The architecture enables a dynamic pivot for its runtime…

Current State-of-the-Art models in Named Entity Recognition (NER) are neural models with a Conditional Random Field (CRF) as the final network layer, and pre-trained "contextual embeddings". The CRF layer is used to facilitate global…

The Transformer architecture has led to significant gains in machine translation. However, most studies focus on only sentence-level translation without considering the context dependency within documents, leading to the inadequacy of…

We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user…

Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…

Context plays a crucial role in visual recognition as it provides complementary clues for different learning tasks including image classification and annotation. As the performances of these tasks are currently reaching a plateau, any extra…

Traditional information retrieval (IR) ranking models process the full text of documents. Newer models based on Transformers, however, would incur a high computational cost when processing long texts, so typically use only snippets from the…

Effective long-term memory management is crucial for language models handling extended contexts. We introduce the Enhanced Ranked Memory Augmented Retrieval (ERMAR) framework, which dynamically ranks memory entries based on relevance.…

Large Language Models employing Chain-of-Thought reasoning achieve strong performance but suffer from excessive token consumption that inflates inference costs. Existing efficiency methods such as explicit length penalties, difficulty…

Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic processes. Originally developed as a scalable alternative to Gaussian Processes (GPs), which are…

Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned…

Existing neural ranking models follow the text matching paradigm, where document-to-query relevance is estimated through predicting the matching score. Drawing from the rich literature of classical generative retrieval models, we introduce…

The strong capabilities of recent Large Language Models (LLMs) have made them highly effective for zero-shot re-ranking task. Attention-based re-ranking methods, which derive relevance scores directly from attention weights, offer an…