Related papers: MURR: Model Updating with Regularized Replay for S…

The online learning of deep neural networks is an interesting problem of machine learning because, for example, major IT companies want to manage the information of the massive data uploaded on the web daily, and this technology can…

Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models…

Topic relevance between query and document is a very important part of social search, which can evaluate the degree of matching between document and user's requirement. In most social search scenarios such as Dianping, modeling search…

Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts,…

Large language models (LLMs) inherently display hallucinations since the precision of generated texts cannot be guaranteed purely by the parametric knowledge they include. Although retrieval-augmented generation (RAG) systems enhance the…

Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…

Our analysis of large summarization datasets indicates that redundancy is a very serious problem when summarizing long documents. Yet, redundancy reduction has not been thoroughly investigated in neural summarization. In this work, we…

Medical systematic reviews typically require assessing all the documents retrieved by a search. The reason is two-fold: the task aims for ``total recall''; and documents retrieved using Boolean search are an unordered set, and thus it is…

Retrieval of live, user-broadcast video streams is an under-addressed and increasingly relevant challenge. The on-line nature of the problem requires temporal evaluation and the unforeseeable scope of potential queries motivates an approach…

The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc…

Document expansion (DE) via query generation tackles vocabulary mismatch in sparse retrieval, yet faces limitations: uncontrolled generation producing hallucinated or redundant queries with low diversity; poor generalization from in-domain…

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both…

Due to the conceptual simplicity, the linear filtering framework, notably the autoregressive (AR) process, has a long history in simulating clutter sequences with specified probability density functions (PDFs) and autocorrelation functions…

Successful Artificial Intelligence systems often require numerous labeled data to extract information from document images. In this paper, we investigate the problem of improving the performance of Artificial Intelligence systems in…

Multi-hop question answering is a challenging task with distinct industrial relevance, and Retrieval-Augmented Generation (RAG) methods based on large language models (LLMs) have become a popular approach to tackle this task. Owing to the…

Retrieval-Augmented Generation (RAG) expands the knowledge of Large Language Models (LLMs), yet current static retrieval methods struggle with complex, multi-hop problems. While recent dynamic retrieval strategies offer improvements, they…

We consider the problem of creating document representations in which inter-document similarity measurements correspond to semantic similarity. We first present a novel subspace-based framework for formalizing this task. Using this…

Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and…

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…

The vocabulary mismatch problem is a long-standing problem in information retrieval. Semantic matching holds the promise of solving the problem. Recent advances in language technology have given rise to unsupervised neural models for…