Related papers: Retrieval for Extremely Long Queries and Documents…

Query performance prediction (QPP) aims to estimate the retrieval quality of a search system for a query without human relevance judgments. Previous QPP methods typically return a single scalar value and do not require the predicted values…

Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep…

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…

Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient…

Question answering represents a core capability of large language models (LLMs). However, when individuals encounter unfamiliar knowledge in texts, they often formulate questions that the text itself cannot answer due to insufficient…

First-stage retrieval is a critical task that aims to retrieve relevant document candidates from a large-scale collection. While existing retrieval models have achieved impressive performance, they are mostly studied on static data sets,…

Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across LLMs under RAG necessitates intelligent routing mechanisms,…

A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC),…

Retrieval-augmented generation (RAG) systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggregating them to generate an answer. Efficiently selecting…

The quality of answers generated by large language models (LLMs) in retrieval-augmented generation (RAG) is largely influenced by the contextual information contained in the retrieved documents. A key challenge for improving RAG is to…

Re-finding files from a personal computer is a frequent demand to users. When encountered a difficult re-finding task, people may not recall the attributes used by conventional re-finding methods, such as a file's path, file name, keywords…

Lowering the numerical precision of model parameters and computations is widely adopted to improve the efficiency of retrieval systems. However, when computing relevance scores between the query and documents in low-precision, we observe…

Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content. To overcome these challenges, we propose a two-step framework, Reconstruct before Summarize (RbS), for effective and…

Hyperparameter tuning is one of the the most time-consuming parts in machine learning. Despite the existence of modern optimization algorithms that minimize the number of evaluations needed, evaluations of a single setting may still be…

In realistic retrieval settings with large and evolving knowledge bases, the total number of documents relevant to a query is typically unknown, and recall cannot be computed. In this paper, we evaluate several established strategies for…

Query-focused summarization (QFS) requires generating a summary given a query using a set of relevant documents. However, such relevant documents should be annotated manually and thus are not readily available in realistic scenarios. To…

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…

Several methods have been proposed for classifying long textual documents using Transformers. However, there is a lack of consensus on a benchmark to enable a fair comparison among different approaches. In this paper, we provide a…

Transformers are not suited for processing long documents, due to their quadratically increasing memory and time consumption. Simply truncating a long document or applying the sparse attention mechanism will incur the context fragmentation…

This paper describes a machine learning algorithm for document (re)ranking, in which queries and documents are firstly encoded using BERT [1], and on top of that a learning-to-rank (LTR) model constructed with TF-Ranking (TFR) [2] is…