相关论文: A Multilingual, Culture-First Approach to Addressi…

Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Misgendering, the act of incorrectly addressing someone's gender, inflicts serious harm and is pervasive in…

Numerous methods have been proposed to measure LLM misgendering, including probability-based evaluations (e.g., automatically with templatic sentences) and generation-based evaluations (e.g., with automatic heuristics or human validation).…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary…

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective…

Automatic Gender Recognition (AGR) systems are an increasingly widespread application in the Machine Learning (ML) landscape. While these systems are typically understood as detecting gender, they often classify datapoints based on…

Gender biases in language generation systems are challenging to mitigate. One possible source for these biases is gender representation disparities in the training and evaluation data. Despite recent progress in documenting this problem and…

Language is far more than a communication tool. A wealth of information - including but not limited to the identities, psychological states, and social contexts of its users - can be gleaned through linguistic markers, and such insights are…

Natural language processing (NLP) has witnessed a profound impact of large language models (LLMs) that excel in a multitude of tasks. However, the limitation of LLMs in multilingual settings, particularly in underrepresented languages,…

Misalignment in Large Language Models (LLMs) refers to the failure to simultaneously satisfy safety, value, and cultural dimensions, leading to behaviors that diverge from human expectations in real-world settings where these dimensions…

Social biases can manifest in language agency. However, very limited research has investigated such biases in Large Language Model (LLM)-generated content. In addition, previous works often rely on string-matching techniques to identify…

The rapid integration of Large Language Models (LLMs) into various domains raises concerns about societal inequalities and information bias. This study examines biases in LLMs related to background, gender, and age, with a focus on their…

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…

Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the…

Large Language Models (LLMs) are acquiring a wider range of capabilities, including understanding and responding in multiple languages. While they undergo safety training to prevent them from answering illegal questions, imbalances in…

Bias is a disproportionate prejudice in favor of one side against another. Due to the success of transformer-based Masked Language Models (MLMs) and their impact on many NLP tasks, a systematic evaluation of bias in these models is needed…

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…

This chapter focuses on gender-related errors in machine translation (MT) in the context of low-resource languages. We begin by explaining what low-resource languages are, examining the inseparable social and computational factors that…

Large language models (LLMs) are being deployed across the Global South, where everyday use involves low-resource languages, code-mixing, and culturally specific norms. Yet safety pipelines, benchmarks, and alignment still largely target…

Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life. Given the recent popularity and adoption of language generation technologies, the potential to further marginalize…