Related papers: Towards Axiomatic Explanations for Neural Ranking …

We study whether visual embedding models capture continuous, ordinal attributes along linear directions, which we term _rank axes_. We define a model as _rankable_ for an attribute if projecting embeddings onto such an axis preserves the…

We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Model1 as an aggregator layer applied to context-free or…

Negation is a fundamental aspect of human communication, yet it remains a challenge for Language Models (LMs) in Information Retrieval (IR). Despite the heavy reliance of modern neural IR systems on LMs, little attention has been given to…

Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is…

Journal ranking is becoming more important in assessing the quality of academic research. Several indices have been suggested for this purpose, typically on the basis of a citation graph between the journals. We follow an axiomatic approach…

Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine the changing reranker…

Ranking individuals based on their performance in different coalitions is a problem emerging in various domains (teams sports, scientific evaluation, argumentation, etc.). Often, for practical reasons, the number of comparable coalitions is…

Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual…

Document reranking is a key component in information retrieval (IR), aimed at refining initial retrieval results to improve ranking quality for downstream tasks. Recent studies--motivated by large reasoning models (LRMs)--have begun…

Recommender systems are tasked to infer users' evolving preferences and rank items aligned with their intents, which calls for in-depth reasoning beyond pattern-based scoring. Recent efforts start to leverage large language models (LLMs)…

Concept explanation is a popular approach for examining how human-interpretable concepts impact the predictions of a model. However, most existing methods for concept explanations are tailored to specific models. To address this issue, this…

In recent years, researchers proposed several algorithms that compute metric quantities of real-world complex networks, and that are very efficient in practice, although there is no worst-case guarantee. In this work, we propose an…

Categorization axioms have been proposed to axiomatizing clustering results, which offers a hint of bridging the difference between human recognition system and machine learning through an intuitive observation: an object should be assigned…

A large-scale recommender system usually consists of recall and ranking modules. The goal of ranking modules (aka rankers) is to elaborately discriminate users' preference on item candidates proposed by recall modules. With the success of…

It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…

Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a…

For ambiguous queries, conventional retrieval systems are bound by two conflicting goals. On the one hand, they should diversify and strive to present results for as many query intents as possible. On the other hand, they should provide…

We propose analyzing conditional reasoning by appeal to a notion of intervention on a simulation program, formalizing and subsuming a number of approaches to conditional thinking in the recent AI literature. Our main results include a…

The application of large language models (LLMs) in recommendation systems has recently gained traction. Traditional recommendation systems often lack explainability and suffer from issues such as popularity bias. Previous research has also…

Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models.…