Related papers: Exposing Bias in Online Communities through Large-…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

Biases induced to text by generative models have become an increasingly large topic in recent years. In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analysis models. For this,…

Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where…

We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text when input prompts…

Content moderation on social media platforms shapes the dynamics of online discourse, influencing whose voices are amplified and whose are suppressed. Recent studies have raised concerns about the fairness of content moderation practices,…

Harmful content detection models tend to have higher false positive rates for content from marginalized groups. In the context of marginal abuse modeling on Twitter, such disproportionate penalization poses the risk of reduced visibility,…

There is a growing collection of work analyzing and mitigating societal biases in language understanding, generation, and retrieval tasks, though examining biases in creative tasks remains underexplored. Creative language applications are…

Sociodemographic biases are a common problem for natural language processing, affecting the fairness and integrity of its applications. Within sentiment analysis, these biases may undermine sentiment predictions for texts that mention…

Culture fundamentally shapes people's reasoning, behavior, and communication. As people increasingly use generative artificial intelligence (AI) to expedite and automate personal and professional tasks, cultural values embedded in AI models…

We investigate bias trends in text-to-image generative models over time, focusing on the increasing availability of models through open platforms like Hugging Face. While these platforms democratize AI, they also facilitate the spread of…

As Large Language Models (LLMs) become widely used to model and simulate human behavior, understanding their biases becomes critical. We developed an experimental framework using Big Five personality surveys and uncovered a previously…

While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…

With the increasing role of Natural Language Processing (NLP) in various applications, challenges concerning bias and stereotype perpetuation are accentuated, which often leads to hate speech and harm. Despite existing studies on sexism and…

User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written…

The increasing use of Large Language Models (LLMs) in a large variety of domains has sparked worries about how easily they can perpetuate stereotypes and contribute to the generation of biased content. With a focus on gender and…

As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across…

We examine whether large language models (LLMs) can predict biased decision-making in conversational settings, and whether their predictions capture not only human cognitive biases but also how those effects change under cognitive load. In…

Advancements in Large Language Models (LLMs) have increased the performance of different natural language understanding as well as generation tasks. Although LLMs have breached the state-of-the-art performance in various tasks, they often…

With the popularity of automatic code generation tools, such as Copilot, the study of the potential hazards of these tools is gaining importance. In this work, we explore the social bias problem in pre-trained code generation models. We…

Social bias in language models can potentially exacerbate social inequalities. Despite it having garnered wide attention, most research focuses on English data. In a low-resource scenario, the models often perform worse due to insufficient…