Zobrazeno 1 - 10
of 435
pro vyhledávání: '"P. Lauscher"'
Warning: this paper contains content that may be offensive or upsetting Hate speech moderation on global platforms poses unique challenges due to the multimodal and multilingual nature of content, along with the varying cultural perceptions. How well
Externí odkaz:
http://arxiv.org/abs/2411.03888
Stereotypical bias encoded in language models (LMs) poses a threat to safe language technology, yet our understanding of how bias manifests in the parameters of LMs remains incomplete. We introduce local contrastive editing that enables the localizat
Externí odkaz:
http://arxiv.org/abs/2410.17739
Autor:
Wingarz, Tatjana, Lauscher, Anne, Edinger, Janick, Kaaser, Dominik, Schulte, Stefan, Fischer, Mathias
Advanced AI applications have become increasingly available to a broad audience, e.g., as centrally managed large language models (LLMs). Such centralization is both a risk and a performance bottleneck - Edge AI promises to be a solution to these pro
Externí odkaz:
http://arxiv.org/abs/2410.05349
Gender-fair language, an evolving German linguistic variation, fosters inclusion by addressing all genders or using neutral forms. Nevertheless, there is a significant lack of resources to assess the impact of this linguistic shift on classification
Externí odkaz:
http://arxiv.org/abs/2409.17929
Autor:
Gautam, Vagrant, Steuer, Julius, Bingert, Eileen, Johns, Ray, Lauscher, Anne, Klakow, Dietrich
While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to evaluate gend
Externí odkaz:
http://arxiv.org/abs/2409.05653
Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment
Large language models (LLMs) increasingly find their way into the most diverse areas of our everyday lives. They indirectly influence people's decisions or opinions through their daily use. Therefore, understanding how and which moral judgements thes
Externí odkaz:
http://arxiv.org/abs/2407.15184
Autor:
Hinck, Musashi, Holtermann, Carolin, Olson, Matthew Lyle, Schneider, Florian, Yu, Sungduk, Bhiwandiwalla, Anahita, Lauscher, Anne, Tseng, Shaoyen, Lal, Vasudev
We uncover a surprising multilingual bias occurring in a popular class of multimodal vision-language models (VLMs). Including an image in the query to a LLaVA-style VLM significantly increases the likelihood of the model returning an English response
Externí odkaz:
http://arxiv.org/abs/2407.02333
The translation of gender-neutral person-referring terms (e.g., the students) is often non-trivial. Translating from English into German poses an interesting case -- in German, person-referring nouns are usually gender-specific, and if the gender of
Externí odkaz:
http://arxiv.org/abs/2406.06131
Personal names simultaneously differentiate individuals and categorize them in ways that are important in a given society. While the natural language processing community has thus associated personal names with sociodemographic characteristics in a v
Externí odkaz:
http://arxiv.org/abs/2405.17159
Texts written in different languages reflect different culturally-dependent beliefs of their writers. Thus, we expect multilingual LMs (MLMs), that are jointly trained on a concatenation of text in multiple languages, to encode different cultural val
Externí odkaz:
http://arxiv.org/abs/2405.12744