相关论文: ML-EAT: A Multilevel Embedding Association Test fo…

With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models generate dynamic word…

Many studies have revealed that word embeddings, language models, and models for specific downstream tasks in NLP are prone to social biases, especially gender bias. Recently these techniques have been gradually applied to automatic…

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases. Measuring such implicit biases can be a challenge: as LLMs…

Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this work, we present the Speech Embedding Association Test…

Theory of Mind (ToM) in Large Language Models (LLMs) refers to the model's ability to infer the mental states of others, with failures in this ability often manifesting as systemic implicit biases. Assessing this challenge is difficult, as…

Language carries implicit human biases, functioning both as a reflection and a perpetuation of stereotypes that people carry with them. Recently, ML-based NLP methods such as word embeddings have been shown to learn such language biases…

We generalize the notion of social biases from language embeddings to grounded vision and language embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungrounded embeddings. This…

When exposed to human-generated data, language models are known to learn and amplify societal biases. While previous works introduced benchmarks that can be used to assess the bias in these models, they rely on assumptions that may not be…

We examine the abilities of intrinsic bias metrics of static word embeddings to predict whether Natural Language Processing (NLP) systems exhibit biased behavior. A word embedding is one of the fundamental NLP technologies that represents…

This paper investigates the subtle and often concealed biases present in Large Language Models (LLMs), focusing on implicit biases that may remain despite passing explicit bias tests. Implicit biases are significant because they influence…

Human biases are ubiquitous but not uniform: disparities exist across linguistic, cultural, and societal borders. As large amounts of recent literature suggest, language models (LMs) trained on human data can reflect and often amplify the…

This paper addresses the issue of implicit stereotypes that may arise during the generation process of large language models. It proposes an interpretable bias detection method aimed at identifying hidden social biases in model outputs,…

Reporting and providing test sets for harmful bias in NLP applications is essential for building a robust understanding of the current problem. We present a new observation of gender bias in a downstream NLP application: marked attribute…

Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to the numerous prior…

The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text…

Implicit biases refer to automatic mental processes that shape perceptions, judgments, and behaviors. Previous research on "implicit bias" in LLMs focused primarily on outputs rather than the processes underlying the outputs. We present the…

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in understanding and generating content across various modalities, such as images and text. However, their interpretability remains a challenge, hindering…

As Large language models (LLMs) become increasingly integrated into our lives, their inherent social biases remain a pressing concern. Detecting and evaluating these biases can be challenging because they are often implicit rather than…

Understanding differences of viewpoints across corpora is a fundamental task for computational social sciences. In this paper, we propose the Sliced Word Embedding Association Test (SWEAT), a novel statistical measure to compute the…