相关论文: Debiasing Gender Bias in Information Retrieval Mod…

Predictive algorithms have a powerful potential to offer benefits in areas as varied as medicine or education. However, these algorithms and the data they use are built by humans, consequently, they can inherit the bias and prejudices…

Machine Learning models have been deployed across many different aspects of society, often in situations that affect social welfare. Although these models offer streamlined solutions to large problems, they may contain biases and treat…

Artificial intelligence (AI) hiring tools have revolutionized resume screening, and large language models (LLMs) have the potential to do the same. However, given the biases which are embedded within LLMs, it is unclear whether they can be…

Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural…

Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to the fact that the training data on which models are built…

The use of Large Language Models (LLMs) in hiring has led to legislative actions to protect vulnerable demographic groups. This paper presents a novel framework for benchmarking hierarchical gender hiring bias in Large Language Models…

Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. The Web likely contains the information necessary to excel…

To mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text…

Definition bias is a negative phenomenon that can mislead models. Definition bias in information extraction appears not only across datasets from different domains but also within datasets sharing the same domain. We identify two types of…

Large Language Models (LLMs) are finding applications in all aspects of life, but their susceptibility to biases, particularly gender stereotyping, raises ethical concerns. This study introduces a novel methodology, a persona-based…

Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been…

Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonly recognized as low-quality, containing inductive biases…

Information Retrieval (IR) systems are designed to deliver relevant content, but traditional systems may not optimize rankings for fairness, neutrality, or the balance of ideas. Consequently, IR can often introduce indexical biases, or…

People frequently interact with information retrieval (IR) systems, however, IR models exhibit biases and discrimination towards various demographics. The in-processing fair ranking methods provide a trade-offs between accuracy and fairness…

Search Engines (SE) have been shown to perpetuate well-known gender stereotypes identified in psychology literature and to influence users accordingly. Similar biases were found encoded in Word Embeddings (WEs) learned from large online…

Pre-trained Language Models have recently emerged in Information Retrieval as providing the backbone of a new generation of neural systems that outperform traditional methods on a variety of tasks. However, it is still unclear to what…

Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large text corpora which…

Gender-inclusive machine translation (MT) should preserve gender ambiguity in the source to avoid misgendering and representational harms. While gender ambiguity often occurs naturally in notional gender languages such as English,…

With the advancement of generation models, AI-generated content (AIGC) is becoming more realistic, flooding the Internet. A recent study suggests that this phenomenon causes source bias in text retrieval for web search. Specifically, neural…

Although large pre-trained language models have achieved great success in many NLP tasks, it has been shown that they reflect human biases from their pre-training corpora. This bias may lead to undesirable outcomes when these models are…