7 papers
Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting
Paweł Mąka, Piotr Andruszkiewicz, Yusuf Can Semerci +2
Multimodal Machine Translation aims to incorporate additional signal from non-textual modalities to improve translations by resolving ambiguities. While models, through multimodal…
Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation
Paweł Mąka, Yusuf Can Semerci, Jan Scholtes +1
In this paper, we introduce a gradient-based head attribution strategy where the Token-level Max-Margin loss is backpropagated to the attention maps. This framework enables a large…
WinoQueer-NL: Assessing Bias in Dutch Language Models toward LGBTQ+ Identities
Jiska Beuk, Gerasimos Spanakis
While English language models have been widely examined for anti-queer bias, Dutch models remain understudied. To address this gap, we developed a culturally and linguistically ada…
Traceable by Design: An LLM Pipeline and Dashboard for EU Regulatory Consultation Analysis
Thales Bertaglia, Haoyang Gui, Catalina Goanta +1
Public consultations generate large volumes of data in the form of stakeholder submissions that are practically unfeasible to analyse manually. We present an end-to-end LLM-based p…
Is your AI Model Accurate Enough? The Difficult Choices Behind Rigorous AI Development and the EU AI Act
Lucas G. Uberti-Bona Marin, Bram Rijsbosch, Kristof Meding +3
Technical and legal debates frequently suggest that "accuracy" is an objective, measurable, and purely technical property. We challenge this view, showing that evaluating AI perfor…
From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models
Abdulmuizz Khalak, Abderrahmane Issam, Gerasimos Spanakis
Arabic Language Models (LMs) are pretrained predominately on Modern Standard Arabic (MSA) and are expected to transfer to its dialects. While MSA as the standard written variety is…
Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text
Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes +1
End-to-End Speech Translation (E2E-ST) has seen significant advancements, yet current models are primarily benchmarked on curated, "clean" datasets. This overlooks critical real-wo…