Related papers: Multi-Feature Integration for Perception-Dependent…

Unbiased Learning to Rank (ULTR) studies the problem of learning a ranking function based on biased user interactions. In this framework, ULTR algorithms have to rely on a large amount of user data that are collected, stored, and aggregated…

Bias can be introduced in diverse ways in machine learning datasets, for example via selection or label bias. Although these bias types in themselves have an influence on important aspects of fair machine learning, their different impact…

Learning to Rank (LTR) models learn from historical user interactions, such as user clicks. However, there is an inherent bias in the clicks of users due to position bias, i.e., users are more likely to click highly-ranked documents than…

When analyzing data researchers make some decisions that are either arbitrary, based on subjective beliefs about the data generating process, or for which equally justifiable alternative choices could have been made. This wide range of…

The Unbiased Learning-to-Rank framework has been recently proposed as a general approach to systematically remove biases, such as position bias, from learning-to-rank models. The method takes two steps - estimating click propensities and…

Most accurate predictions are typically obtained by learning machines with complex feature spaces (as e.g. induced by kernels). Unfortunately, such decision rules are hardly accessible to humans and cannot easily be used to gain insights…

Metaphors are pervasive in communication, making them crucial for natural language processing (NLP). Previous research on automatic metaphor processing predominantly relies on training data consisting of English samples, which often reflect…

As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric evaluations neglect the visual modality, leaving an unregulated channel for latent social…

Learning-to-Rank (LTR) models trained from implicit feedback (e.g. clicks) suffer from inherent biases. A well-known one is the position bias -- documents in top positions are more likely to receive clicks due in part to their position…

Societal biases that are contained in retrieved documents have received increased interest. Such biases, which are often prevalent in the training data and learned by the model, can cause societal harms, by misrepresenting certain groups,…

Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias often leads to unexpected model failures and hurts performance,…

Estimating position bias is a well-known challenge in Learning to Rank (L2R). Click data in e-commerce applications, such as targeted advertisements and search engines, provides implicit but abundant feedback to improve personalized…

The page presentation biases in the information retrieval system, especially on the click behavior, is a well-known challenge that hinders improving ranking models' performance with implicit user feedback. Unbiased Learning to Rank~(ULTR)…

To be discoverable in an embedding-based search process, each part of a document should be reflected in its embedding representation. To quantify any potential reflection biases, we introduce a permutation-based evaluation framework. With…

Unbiased learning to rank (ULTR) aims to mitigate various biases existing in user clicks, such as position bias, trust bias, presentation bias, and learn an effective ranker. In this paper, we introduce our winning approach for the…

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We propose…

Text matching systems have become a fundamental service in most searching platforms. For instance, they are responsible for matching user queries to relevant candidate items, or rewriting the user-input query to a pre-selected…

In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…

Information fusion is used widely to improve document classification by the integration of multiple data sources (multimodal) or representations (multiview). However, the field lacks a unified framework, a quantitative synthesis of its…

This paper presents a machine learning approach to multidimensional item response theory (MIRT), a class of latent factor models that can be used to model and predict student performance from observed assessment data. Inspired by…