Related papers: Reverse-Engineering the Retrieval Process in GenIR…

Neural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice. However, neural systems lack the interpretability of bag-of-words models; it is not trivial to connect a query change to…

Phase retrieval is a nonlinear inverse problem that arises in a wide range of imaging modalities, from electron microscopy to Fourier ptychography. In particular, the reconstruction is facilitated when the sensing matrix is i.i.d. random,…

Pretrained language models (PLMs) like BERT and GPT-4 have become the foundation for modern information retrieval (IR) systems. However, existing PLM-based IR models primarily rely on the knowledge learned during training for prediction,…

Generative retrieval has recently emerged as a promising approach to sequential recommendation, framing candidate item retrieval as an autoregressive sequence generation problem. However, existing generative methods typically focus solely…

This decade has seen a great deal of progress in the development of information retrieval systems. Unfortunately, we still lack a systematic understanding of the behavior of the systems and their relationship with documents. In this paper…

Ever-larger language models with ever-increasing capabilities are by now well-established text processing tools. Alas, information extraction tasks such as named entity recognition are still largely unaffected by this progress as they are…

Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex…

When combined with In-Context Learning, a technique that enables models to adapt to new tasks by incorporating task-specific examples or demonstrations directly within the input prompt, autoregressive language models have achieved good…

The convergence of generative AI and web search is reshaping problem-solving for programmers. However, the lack of understanding regarding their interplay in the information-seeking process often leads programmers to perceive them as…

Recent years have witnessed a substantial increase in the use of deep learning to solve various natural language processing (NLP) problems. Early deep learning models were constrained by their sequential or unidirectional nature, such that…

Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding space for effective retrieval. However, most existing methods…

Generative retrieval (GR) has gained significant attention as an effective paradigm that integrates the capabilities of large language models (LLMs). It generally consists of two stages: constructing discrete semantic identifiers (IDs) for…

Retrieval-Augmented Generation (RAG) improves factual grounding in large language models but suffers from substantial latency due to synchronous retrieval. While recent work explores asynchronous retrieval, existing approaches rely on…

While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling…

Dense retrieval is a crucial task in Information Retrieval (IR), serving as the basis for downstream tasks such as re-ranking and augmenting generation. Recently, large language models (LLMs) have demonstrated impressive semantic…

The main objective of an Information Retrieval system is to provide a user with the most relevant documents to the user's query. To do this, modern IR systems typically deploy a re-ranking pipeline in which a set of documents is retrieved…

Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vectors generated by…

Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first…

The synergy between generative and discriminative models receives growing attention. While discriminative Contrastive Language-Image Pre-Training (CLIP) excels in high-level semantics, it struggles with perceiving fine-grained visual…

Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external…