相关论文: Understanding and Countering Stereotypes: A Comput…

The Stereotype Content model (SCM) states that we tend to perceive minority groups as cold, incompetent or both. In this paper we adapt existing work to demonstrate that the Stereotype Content model holds for contextualised word embeddings,…

Existing word embedding debiasing methods require social-group-specific word pairs (e.g., "man"-"woman") for each social attribute (e.g., gender), which cannot be used to mitigate bias for other social groups, making these methods…

Large Language Models (LLMs) have been observed to encode and perpetuate harmful associations present in the training data. We propose a theoretically grounded framework called StereoMap to gain insights into their perceptions of how…

As large vision language models(LVLMs) rapidly advance, concerns about their potential to learn and generate social biases and stereotypes are increasing. Previous studies on LVLM's stereotypes face two primary limitations: metrics that…

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…

Warning: this paper contains material which may be offensive or upsetting. While much of recent work has focused on the detection of hate speech and overtly offensive content, very little research has explored the more subtle but equally…

This study introduces a taxonomy of stereotype content in contemporary large language models (LLMs). We prompt ChatGPT 3.5, Llama 3, and Mixtral 8x7B, three powerful and widely used LLMs, for the characteristics associated with 87 social…

Recently, language models have demonstrated strong performance on various natural language understanding tasks. Language models trained on large human-generated corpus encode not only a significant amount of human knowledge, but also the…

We describe a computational model of social norms based on identifying values that a certain culture finds desirable such as dignity, generosity and politeness. The model quantifies these values in the form of Culture-Sanctioned Social…

Social categories and stereotypes are embedded in language and can introduce data bias into Large Language Models (LLMs). Despite safeguards, these biases often persist in model behavior, potentially leading to representational harm in…

Static word embeddings often absorb social biases from the text they learn from, and those biases can quietly shape downstream systems. Prior work that uses the Stereotype Content Model (SCM) has focused mostly on single-group bias along…

The rapid increase in hate speech on social media has exposed an unprecedented impact on society, making automated methods for detecting such content important. Unlike prior black-box models, we propose a novel transparent method for…

In social psychology and cognitive science, there has been much interest in studying category stereotypes. However, we still lack a consensual mathematical definition or framework, which is necessary for us to hold a deeper understanding of…

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…

In this paper, we introduce a novel semantic description approach inspired on Prototype Theory foundations. We propose a Computational Prototype Model (CPM) that encodes and stores the central semantic meaning of objects category: the…

Stereotypes influence social perceptions and can escalate into discrimination and violence. While NLP research has extensively addressed gender bias and hate speech, stereotype detection remains an emerging field with significant societal…

In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned with deep learning models. Motivated by the human approach to…

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,…

Cutting-edge image generation has been praised for producing high-quality images, suggesting a ubiquitous future in a variety of applications. However, initial studies have pointed to the potential for harm due to predictive bias,…

Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training…