In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT) on medical notes from the MIMIC-III hospital dataset, and quantify potential disparities using two approaches. First, we identify dangerous latent relationships that are captured by the contextual word embeddings using a fill-in-the-blank method with text from real clinical notes and a log probability bias score quantification. Second, we evaluate performance gaps across different definitions of fairness on over 50 downstream clinical prediction tasks that include detection of acute and chronic conditions. We find that classifiers trained from BERT representations exhibit statistically significant differences in performance, often favoring the majority group with regards to gender, language, ethnicity, and insurance status. Finally, we explore shortcomings of using adversarial debiasing to obfuscate subgroup information in contextual word embeddings, and recommend best practices for such deep embedding models in clinical settings.
In this work, we consider how preference models in interactive recommendation systems determine the availability of content and users' opportunities for discovery. We propose an evaluation procedure based on stochastic reachability to quantify the maximum probability of recommending a target piece of content to an user for a set of allowable strategic modifications. This framework allows us to compute an upper bound on the likelihood of recommendation with minimal assumptions about user behavior. Stochastic reachability can be used to detect biases in the availability of content and diagnose l…
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；TU Berlin（柏林工业大学）
An increasing awareness of biased patterns in natural language processing resources, like BERT, has motivated many metrics to quantify `bias' and `fairness'. But comparing the results of different metrics and the works that evaluate with such metrics remains difficult, if not outright impossible. We survey the existing literature on fairness metrics for pretrained language models and experimentally evaluate compatibility, including both biases in language models as in their downstream tasks. We do this by a mixture of traditional literature survey and correlation analysis, as well as by runnin…
Recently, there has been an increase in efforts to understand how large language models (LLMs) propagate and amplify social biases. Several works have utilized templates for fairness evaluation, which allow researchers to quantify social biases in the absence of test sets with protected attribute labels. While template evaluation can be a convenient and helpful diagnostic tool to understand model deficiencies, it often uses a simplistic and limited set of templates. In this paper, we study whether bias measurements are sensitive to the choice of templates used for benchmarking. Specifically, w…
The closed feedback loop in recommender systems is a common setting that can lead to different types of biases. Several studies have dealt with these biases by designing methods to mitigate their effect on the recommendations. However, most existing studies do not consider the iterative behavior of the system where the closed feedback loop plays a crucial role in incorporating different biases into several parts of the recommendation steps. We present a theoretical framework to model the asymptotic evolution of the different components of a recommender system operating within a feedback loop s…
University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）
Warning: this paper contains content that may be offensive or upsetting. Numerous natural language processing models have tried injecting commonsense by using the ConceptNet knowledge base to improve performance on different tasks. ConceptNet, however, is mostly crowdsourced from humans and may reflect human biases such as "lawyers are dishonest." It is important that these biases are not conflated with the notion of commonsense. We study this missing yet important problem by first defining and quantifying biases in ConceptNet as two types of representational harms: overgeneralization of polar…
Measuring bias is key for better understanding and addressing unfairness in NLP/ML models. This is often done via fairness metrics which quantify the differences in a model's behaviour across a range of demographic groups. In this work, we shed more light on the differences and similarities between the fairness metrics used in NLP. First, we unify a broad range of existing metrics under three generalized fairness metrics, revealing the connections between them. Next, we carry out an extensive empirical comparison of existing metrics and demonstrate that the observed differences in bias measure…
Wharton School, University of Pennsylvania（宾夕法尼亚大学沃顿商学院）
Cultural items like songs have an important impact in creating and reinforcing stereotypes, biases, and discrimination. But the actual nature of such items is often less transparent. Take songs, for example. Are lyrics biased against women? And how have any such biases changed over time? Natural language processing of a quarter of a million songs over 50 years quantifies misogyny. Women are less likely to be associated with desirable traits (i.e., competence), and while this bias has decreased, it persists. Ancillary analyses further suggest that song lyrics may help drive shifts in societal s…
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
Shanghai AI Laboratory（上海人工智能实验室）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）；School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；School of Computer Science, Fudan University（复旦大学计算机科学技术学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Boston University（波士顿大学）；Microsoft Research New England（微软新英格兰研究院）
Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these stereotypes. In this paper, we initiate the study of gender stereotypes in {\em word embedding}, a popular framework to represent text data. As their use becomes increasingly common, applications can inadvertently amplify unwanted stereotypes. We show across multiple datasets that the embeddings contain significant gender stereotypes, especially with regard to profe…
Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Pennsylvania（宾夕法尼亚大学）；Huazhong University of Science and Technology（华中科技大学）；Hong Kong Polytechnic University（香港理工大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）
Georgetown University（乔治城大学）；University of Washington（华盛顿大学）
Word embeddings learn implicit biases from linguistic regularities captured by word co-occurrence statistics. By extending methods that quantify human-like biases in word embeddings, we introduceValNorm, a novel intrinsic evaluation task and method to quantify the valence dimension of affect in human-rated word sets from social psychology. We apply ValNorm on static word embeddings from seven languages (Chinese, English, German, Polish, Portuguese, Spanish, and Turkish) and from historical English text spanning 200 years. ValNorm achieves consistently high accuracy in quantifying the valence o…
Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these biases while keeping the syntactic and semantic utility of embeddings intact. This paper describes Fair Embedding Engine (FEE), a library for analysing and mitigating gender bias in word embeddings. FEE combines various state of the art techniques for quantifying, visualising and mitigating gender bias in word embeddings under a standard abstraction. FEE wi…
The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs
1 Department of Speech, Music；Hearing, KTH Royal Institute of Technology, Sweden 2 Centre for Speech Technology Research, University of Edinburgh, UK 3 Texas A\&M University, USA
With the vast development and employment of artificial intelligence applications, research into the fairness of these algorithms has been increased. Specifically, in the natural language processing domain, it has been shown that social biases persist in word embeddings and are thus in danger of amplifying these biases when used. As an example of social bias, religious biases are shown to persist in word embeddings and the need for its removal is highlighted. This paper investigates the state-of-the-art multiclass debiasing techniques: Hard debiasing, SoftWEAT debiasing and Conceptor debiasing.…
