English
Related papers

Related papers: Measuring Harmful Representations in Scandinavian …

200 papers

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…

Computation and Language · Computer Science 2025-10-27 Mojca Brglez , Špela Vintar

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…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Yusuke Hirota , Yuta Nakashima , Noa Garcia

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…

Cryptography and Security · Computer Science 2024-10-18 Yiming Zhang , Javier Rando , Ivan Evtimov , Jianfeng Chi , Eric Michael Smith , Nicholas Carlini , Florian Tramèr , Daphne Ippolito

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…

Artificial Intelligence · Computer Science 2025-01-17 Huandong Wang , Wenjie Fu , Yingzhou Tang , Zhilong Chen , Yuxi Huang , Jinghua Piao , Chen Gao , Fengli Xu , Tao Jiang , Yong Li

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…

Computation and Language · Computer Science 2022-05-23 Tejas Srinivasan , Yonatan Bisk

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.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-22 Yi-Cheng Lin , Tzu-Quan Lin , Chih-Kai Yang , Ke-Han Lu , Wei-Chih Chen , Chun-Yi Kuan , Hung-yi Lee

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.,…

Social and Information Networks · Computer Science 2024-07-02 Vahid Ghafouri , Jose Such , Guillermo Suarez-Tangil

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…

Computation and Language · Computer Science 2024-03-28 Daniel Fesalbon , Arvin De La Cruz , Marvin Mallari , Nelson Rodelas

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,…

Computation and Language · Computer Science 2024-05-31 Luiza Pozzobon , Patrick Lewis , Sara Hooker , Beyza Ermis

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…

Computation and Language · Computer Science 2023-09-04 Vishesh Thakur

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…

Computation and Language · Computer Science 2022-04-14 Emanuele Brugnoli , Rosaria Simone , Marco Delmastro

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…

Computation and Language · Computer Science 2025-07-25 Yuen Chen , Vethavikashini Chithrra Raghuram , Justus Mattern , Rada Mihalcea , Zhijing Jin

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…

Computation and Language · Computer Science 2024-11-18 Michael Döll , Markus Döhring , Andreas Müller

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…

Computation and Language · Computer Science 2021-04-19 Adithya Renduchintala , Adina Williams

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.…

Computation and Language · Computer Science 2024-10-08 Beatrice Savoldi , Sara Papi , Matteo Negri , Ana Guerberof , Luisa Bentivogli

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…

Computation and Language · Computer Science 2025-07-03 Jose A. Diaz-Garcia , Joao Paulo Carvalho

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…

Computation and Language · Computer Science 2026-03-10 Jenny Kunz , Anja Jarochenko , Marcel Bollmann

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…

Computation and Language · Computer Science 2025-05-12 Dawid Wisniewski , Antoni Solarski , Artur Nowakowski

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…

Computation and Language · Computer Science 2021-09-13 Shahar Levy , Koren Lazar , Gabriel Stanovsky

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,…

Human-Computer Interaction · Computer Science 2025-07-09 Aimen Gaba , Emily Wall , Tejas Ramkumar Babu , Yuriy Brun , Kyle Hall , Cindy Xiong Bearfield