相关论文: Measuring Harmful Representations in Scandinavian …

Moral norms vary across cultures. A recent line of work suggests that English large language models contain human-like moral biases, but these studies typically do not examine moral variation in a diverse cultural setting. We investigate…

Recently, much work has concerned itself with the enigma of what exactly pretrained language models~(PLMs) learn about different aspects of language, and how they learn it. One stream of this type of research investigates the knowledge that…

Gender stereotypes are pervasive beliefs about individuals based on their gender that play a significant role in shaping societal attitudes, behaviours, and even opportunities. Recognizing the negative implications of gender stereotypes,…

Prior research has demonstrated that language models can, to a limited extent, represent moral norms in a variety of cultural contexts. This research aims to replicate these findings and further explore their validity, concentrating on…

Classifiers tend to propagate biases present in the data on which they are trained. Hence, it is important to understand how the demographic identities of the annotators of comments affect the fairness of the resulting model. In this paper,…

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…

Translation systems, including foundation models capable of translation, can produce errors that result in gender mistranslation, and such errors can be especially harmful. To measure the extent of such potential harms when translating into…

Natural-language assistants are designed to provide users with helpful responses while avoiding harmful outputs, largely achieved through alignment to human preferences. Yet there is limited understanding of whether alignment techniques may…

Many measures of societal bias in language models have been proposed in recent years. A popular approach is to use a set of word filling prompts to evaluate the behavior of the language models. In this work, we analyze the validity of two…

The recent increase in data and model scale for language model pre-training has led to huge training costs. In scenarios where new data become available over time, updating a model instead of fully retraining it would therefore provide…

Language models are trained mostly on Web data, which often contains social stereotypes and biases that the models can inherit. This has potentially negative consequences, as models can amplify these biases in downstream tasks or…

Language models are trained on large-scale corpora that embed implicit biases documented in psychology. Valence associations (pleasantness/unpleasantness) of social groups determine the biased attitudes towards groups and concepts in social…

Self-supervised models for speech processing emerged recently as popular foundation blocks in speech processing pipelines. These models are pre-trained on unlabeled audio data and then used in speech processing downstream tasks such as…

Large language models (LLMs) have been shown to propagate and amplify harmful stereotypes, particularly those that disproportionately affect marginalised communities. To understand the effect of these stereotypes more comprehensively, we…

The vector representation of words, known as word embeddings, has opened a new research approach in linguistic studies. These representations can capture different types of information about words. The grammatical gender of nouns is a…

Model-based evaluation metrics (e.g., CLIPScore and GPTScore) have demonstrated decent correlations with human judgments in various language generation tasks. However, their impact on fairness remains largely unexplored. It is widely…

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability. We show, however, with a new diagnostic…

Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…

Deep learning based visual-linguistic multimodal models such as Contrastive Language Image Pre-training (CLIP) have become increasingly popular recently and are used within text-to-image generative models such as DALL-E and Stable…

A stereotype is a generalized perception of a specific group of humans. It is often potentially encoded in human language, which is more common in texts on social issues. Previous works simply define a sentence as stereotypical and…