Related papers: Generative Retrieval as Multi-Vector Dense Retriev…

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

Search engines rely heavily on term-based approaches that represent queries and documents as bags of words. Text---a document or a query---is represented by a bag of its words that ignores grammar and word order, but retains word frequency…

Recently, several dense retrieval (DR) models have demonstrated competitive performance to term-based retrieval that are ubiquitous in search systems. In contrast to term-based matching, DR projects queries and documents into a dense vector…

Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic…

This paper concerns a deep learning approach to relevance ranking in information retrieval (IR). Existing deep IR models such as DSSM and CDSSM directly apply neural networks to generate ranking scores, without explicit understandings of…

The advent of LLMs has given rise to a new type of web search: Generative search, where LLMs retrieve web pages related to a query and generate a single, coherent text as a response. This output modality stands in stark contrast to…

We present {\em generative clustering} (GC) for clustering a set of documents, $\mathrm{X}$, by using texts $\mathrm{Y}$ generated by large language models (LLMs) instead of by clustering the original documents $\mathrm{X}$. Because LLMs…

Document retrieval has been an important research problem over many years in the information retrieval community. State-of-the-art techniques utilize various methods in matching documents to a given document including keywords, phrases, and…

Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus only on optimizing…

This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access". The goal of the task is to generate…

Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data. Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the…

Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval…

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…

Addressing the complexity of comprehensive information retrieval, this study introduces an innovative, iterative retrieval-augmented generation system. Our approach uniquely integrates a vector-space driven re-ranking mechanism with…

In any ranking system, the retrieval model outputs a single score for a document based on its belief on how relevant it is to a given search query. While retrieval models have continued to improve with the introduction of increasingly…

Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast approximate nearest neighbor algorithms. As the tasks dense…

Relevance feedback techniques assume that users provide relevance judgments for the top k (usually 10) documents and then re-rank using a new query model based on those judgments. Even though this is effective, there has been little…

Semantic search in retrieval-augmented generation (RAG) systems is often insufficient for complex information needs, particularly when relevant evidence is scattered across multiple sources. Prior approaches to this problem include agentic…

Generative retrieval (Wang et al., 2022; Tay et al., 2022) is a popular approach for end-to-end document retrieval that directly generates document identifiers given an input query. We introduce summarization-based document IDs, in which…

Generative models trained at scale can now produce text, video, and more recently, scientific data such as crystal structures. In applications of generative approaches to materials science, and in particular to crystal structures, the…