Related papers: On Coherence-based Predictors for Dense Query Perf…

A query performance predictor estimates the retrieval effectiveness of an IR system for a given query. An important characteristic of QPP evaluation is that, since the ground truth retrieval effectiveness for QPP evaluation can be measured…

Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and…

The advent of contextualised language models has brought gains in search effectiveness, not just when applied for re-ranking the output of classical weighting models such as BM25, but also when used directly for passage indexing and…

According to the Probability Ranking Principle (PRP), ranking documents in decreasing order of their probability of relevance leads to an optimal document ranking for ad-hoc retrieval. The PRP holds when two conditions are met: [C1] the…

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We…

Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affects downstream tasks. We conduct the first analysis of the…

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…

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…

Large Language Models (LLMs) have made query reformulation ubiquitous in modern retrieval and Retrieval-Augmented Generation (RAG) pipelines, enabling the generation of multiple semantically equivalent query variants. However, executing the…

Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original information need, thus hurting the retrieval effectiveness of…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Conversational search supports multi-turn user-system interactions to solve complex information needs. Different from the traditional single-turn ad-hoc search, conversational search encounters a more challenging problem of…

Term-based ranking with pre-trained transformer-based language models has recently gained attention as they bring the contextualization power of transformer models into the highly efficient term-based retrieval. In this work, we examine the…

The recent advancement in language representation modeling has broadly affected the design of dense retrieval models. In particular, many of the high-performing dense retrieval models evaluate representations of query and document using…

Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization…

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…

Pseudo-Relevance Feedback (PRF) utilises the relevance signals from the top-k passages from the first round of retrieval to perform a second round of retrieval aiming to improve search effectiveness. A recent research direction has been the…

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently. In the mean time, the importance and usefulness to…

Agentic Retrieval-Augmented Generation (RAG) is a new paradigm where the reasoning model decides when to invoke a retriever (as a "tool") when answering a question. This paradigm, exemplified by recent research works such as Search-R1,…