Related papers: Integrating Listwise Ranking into Pairwise-based I…
We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are…
Numerous neural retrieval models have been proposed in recent years. These models learn to compute a ranking score between the given query and document. The majority of existing models are trained in pairwise fashion using human-judged…
Large Language Models (LLMs) have demonstrated exceptional performance in the task of text ranking for information retrieval. While Pointwise ranking approaches offer computational efficiency by scoring documents independently, they often…
Learning to Rank (LTR) methods are vital in online economies, affecting users and item providers. Fairness in LTR models is crucial to allocate exposure proportionally to item relevance. Widely used deterministic LTR models can lead to…
Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and…
Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR). So far neural representation learning has not been extended to meta-textual information that is readily…
Pairwise ranking methods are the basis of many widely used discriminative training approaches for structure prediction problems in natural language processing(NLP). Decomposing the problem of ranking hypotheses into pairwise comparisons…
Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to…
Learning-to-rank (LTR) algorithms are ubiquitous and necessary to explore the extensive catalogs of media providers. To avoid the user examining all the results, its preferences are used to provide a subset of relatively small size. The…
Instance-level image retrieval is the task of searching in a large database for images that match an object in a query image. To address this task, systems usually rely on a retrieval step that uses global image descriptors, and a…
Reranking algorithms have made progress in improving document retrieval quality by efficiently aggregating relevance judgments generated by large language models (LLMs). However, identifying relevant documents for queries that require…
The question of aggregating pair-wise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g. MSR's TrueSkill system) and chess players, aggregating…
While standard IR models are mainly designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly…
In this paper, we consider large-scale ranking problems where one is given a set of (possibly non-redundant) pairwise comparisons and the underlying ranking explained by those comparisons is desired. We show that stochastic gradient descent…
In this work, we propose a theory for information matching. It is motivated by the observation that retrieval is about the relevance matching between two sets of properties (features), namely, the information need representation and…
Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful sequence-to-sequence models such as T5. Existing attempts…
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By…
This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples. In contrast to the standard InfoNCE loss, which requires a strict…
Given a graph where vertices represent alternatives and arcs represent pairwise comparison data, the statistical ranking problem is to find a potential function, defined on the vertices, such that the gradient of the potential function…
Traditional Information Retrieval (IR) metrics, such as nDCG, MAP, and MRR, assume that human users sequentially examine documents with diminishing attention to lower ranks. This assumption breaks down in Retrieval Augmented Generation…