Related papers: Bottleneck-Minimal Indexing for Generative Documen…

Classical information retrieval (IR) methods, such as query likelihood and BM25, score documents independently w.r.t. each query term, and then accumulate the scores. Assuming query term independence allows precomputing term-document scores…

Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and…

Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical,…

Generative retrieval (GR) reformulates the Information Retrieval (IR) task as the generation of document identifiers (docIDs). Despite its promise, existing GR models exhibit poor generalization to newly added documents, often failing to…

In this work, a new indexing technique of data streams called BSTree is proposed. This technique uses the method of data discretization, SAX [4], to reduce online the dimensionality of data streams. It draws on Btree to build the index and…

Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and generalization. Notably, methods like TIGER employing…

Interpretability in black-box dense retrievers remains a central challenge in Retrieval-Augmented Generation (RAG). Understanding how queries and documents semantically interact is critical for diagnosing retrieval behavior and improving…

We study the problem of recovery of matrices that are simultaneously low rank and row and/or column sparse. Such matrices appear in recent applications in cognitive neuroscience, imaging, computer vision, macroeconomics, and genetics. We…

Document retrieval systems have experienced a revitalized interest with the advent of retrieval-augmented generation (RAG). RAG architecture offers a lower hallucination rate than LLM-only applications. However, the accuracy of the…

Retrieval-Augmented Generation (RAG) enhances the response capabilities of language models by integrating external knowledge sources. However, document chunking as an important part of RAG system often lacks effective evaluation tools. This…

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic…

Differentiable Architecture Search (DARTS) has attracted considerable attention as a gradient-based neural architecture search method. Since the introduction of DARTS, there has been little work done on adapting the action space based on…

Retrieval-Augmented Generation (RAG) struggles on long, structured financial filings where relevant evidence is sparse and cross-referenced. This paper presents a systematic investigation of advanced metadata-driven Retrieval-Augmented…

Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing GR models commonly…

In this chapter, we consider generative information retrieval evaluation from two distinct but interrelated perspectives. First, large language models (LLMs) themselves are rapidly becoming tools for evaluation, with current research…

The central challenge of reasoning-intensive retrieval lies in identifying implicitreasoning relationships between queries and documents, rather than superficial se-mantic or lexical similarity. The contrastive learning paradigm is…

As computers approach the physical limits of information storable in memory, new methods will be needed to further improve information storage and retrieval. We propose a quantum inspired vector based approach, which offers a contextually…

Avoiding overfitting is a central challenge in machine learning, yet many large neural networks readily achieve zero training loss. This puzzling contradiction necessitates new approaches to the study of overfitting. Here we quantify…

Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training…

Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, but data not deemed important during training is forgotten,…