Related papers: Measuring Harmful Representations in Scandinavian …
Large language models are demonstrating increasing capabilities, excelling at benchmarks once considered very difficult. As their capabilities grow, there is a need for more challenging evaluations that go beyond surface-level linguistic…
Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing…
Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and…
While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…
Numerous works have analyzed biases in vision and pre-trained language models individually - however, less attention has been paid to how these biases interact in multimodal settings. This work extends text-based bias analysis methods to…
Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability.…
The online trend of the manosphere and feminist discourse on social networks requires a holistic measure of the level of sexism in an online community. This indicator is important for policymakers and moderators of online communities (e.g.,…
Common problems in playing online mobile and computer games were related to toxic behavior and abusive communication among players. Based on different reports and studies, the study also discusses the impact of online hate speech and…
To date, toxicity mitigation in language models has almost entirely been focused on single-language settings. As language models embrace multilingual capabilities, it's crucial our safety measures keep pace. Recognizing this research gap,…
Gender bias in artificial intelligence (AI) and natural language processing has garnered significant attention due to its potential impact on societal perceptions and biases. This research paper aims to analyze gender bias in Large Language…
The media attention to the personal sphere of famous and important individuals has become a key element of the gender narrative. Here we combine lexical, syntactic and sentiment analysis to investigate the role of gender in the…
Generated texts from large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. These findings motivate research efforts aiming to understand and measure such effects. This…
Gender bias in artificial intelligence has become an important issue, particularly in the context of language models used in communication-oriented applications. This study examines the extent to which Large Language Models (LLMs) exhibit…
Transformer based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by…
Gender bias in machine translation (MT) is recognized as an issue that can harm people and society. And yet, advancements in the field rarely involve people, the final MT users, or inform how they might be impacted by biased technologies.…
The success of social media platforms has facilitated the emergence of various forms of online abuse within digital communities. This abuse manifests in multiple ways, including hate speech, cyberbullying, emotional abuse, grooming, and…
Translations often carry traces of the source language, a phenomenon known as translationese. We introduce the first freely available English-to-Swedish dataset contrasting translationese sentences with idiomatic alternatives, designed to…
Recent language models can successfully solve various language-related tasks, and many understand inputs stated in different languages. In this paper, we explore the performance of 17 popular models used to correct grammatical issues in…
Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale…
Large language models (LLMs) are becoming increasingly ubiquitous in our daily lives, but numerous concerns about bias in LLMs exist. This study examines how gender-diverse populations perceive bias, accuracy, and trustworthiness in LLMs,…