Related papers: Dense Retrieval with Continuous Explicit Feedback …

Time is an important relevance signal when searching streams of social media posts. The distribution of document timestamps from the results of an initial query can be leveraged to infer the distribution of relevant documents, which can…

Generative retrieval shed light on a new paradigm of document retrieval, aiming to directly generate the identifier of a relevant document for a query. While it takes advantage of bypassing the construction of auxiliary index structures,…

With the recent advancements in information technology there has been a huge surge in amount of data available. But information retrieval technology has not been able to keep up with this pace of information generation resulting in over…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biases -- including brevity, position, literal matching, and repetition biases -- that can compromise retrieval quality. Query rewriting techniques are now…

Identifying critical research within the growing body of academic work is an intrinsic aspect of conducting quality research. Systematic review processes used in evidence-based medicine formalise this as a procedure that must be followed in…

Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

Modern retrieval pipelines increasingly rely on query reformulation and neural reranking to improve effectiveness, but this comes at a significant computational cost and introduces a fundamental tradeoff between recall and query drift.…

Neural models have demonstrated remarkable performance across diverse ranking tasks. However, the processes and internal mechanisms along which they determine relevance are still largely unknown. Existing approaches for analyzing neural…

Prompt tuning attempts to update few task-specific parameters in pre-trained models. It has achieved comparable performance to fine-tuning of the full parameter set on both language understanding and generation tasks. In this work, we study…

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Systematic reviews require the use of rigorously designed search strategies to ensure both comprehensive retrieval and minimization of bias. Conventional manual approaches, although methodologically systematic, are resource-intensive and…

Technology-Assisted Review (TAR) aims to reduce the human effort required for screening processes such as abstract screening for systematic literature reviews. Human reviewers label documents as relevant or irrelevant during this process,…

In this paper we present Large Language Model Assisted Retrieval Model Ranking (LARMOR), an effective unsupervised approach that leverages LLMs for selecting which dense retriever to use on a test corpus (target). Dense retriever selection…

Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and…

We propose a novel mode of feedback for image search, where a user describes which properties of exemplar images should be adjusted in order to more closely match his/her mental model of the image sought. For example, perusing image results…

The search of information in large text repositories has been plagued by the so-called document-query vocabulary gap, i.e. the semantic discordance between the contents in the stored document entities on the one hand and the human query on…

Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach…

Legal case retrieval, which aims to retrieve relevant cases to a given query case, benefits judgment justice and attracts increasing attention. Unlike generic retrieval queries, legal case queries are typically long and the definition of…