1 citations · 1 across the 11 of their papers we have counts for
12 papers
Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation
Mario Sanz-Guerrero, Minh Duc Bui, Manuel Mager +1
Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked factor: the hidden injection…
Perspectives on Cross-Lingual Consistency in LLMs for Medical Questions
Minh Duc Bui, Mario Sanz-Guerrero, Abteen Ebrahimi +4
Should multilingual LLMs answer medical questions consistently across input languages, or adapt responses to cultural cues? Existing multilingual medical benchmarks usually assume…
From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation
Minh Duc Bui, Xenia Heilmann, Mattia Cerrato +2
Prior work evaluates code generation bias primarily through simple conditional statements, which represent only a narrow slice of real-world programming and reveal solely overt, ex…
Greater accessibility can amplify discrimination in generative AI
Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou +3
Hundreds of millions of people rely on large language models (LLMs) for education, work, and even healthcare. Yet these models are known to reproduce and amplify social biases pres…
Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect
Minh Duc Bui, Manuel Mager, Peter Herbert Kann +1
Meenzerisch, the dialect spoken in the German city of Mainz, is also the traditional language of the Mainz carnival, a yearly celebration well known throughout Germany. However, Me…
NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation
Hossain Shaikh Saadi, Faria Alam, Mario Sanz-Guerrero +3
This paper presents JGU Mainz's winning system for the BLP-2025 Shared Task on Code Generation from Bangla Instructions. We propose a multi-agent-based pipeline. First, a code-gene…
JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA
Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero +1
This paper presents the JGU Mainz submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: Machine Translation and Question Answering, focusing on U…
Large Language Models Discriminate Against Speakers of German Dialects
Minh Duc Bui, Carolin Holtermann, Valentin Hofmann +2
Dialects represent a significant component of human culture and are found across all regions of the world. In Germany, more than 40% of the population speaks a regional dialect (Ad…
On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures
Minh Duc Bui, Kyung Eun Park, Goran Glavaš +2
Measurement systems (e.g., currencies) differ across cultures, but the conversions between them are well defined so that humans can state facts using any measurement system of thei…
Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models
Minh Duc Bui, Katharina von der Wense, Anne 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 na…
The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification
Minh Duc Bui, Katharina von der Wense
Current natural language processing (NLP) research tends to focus on only one or, less frequently, two dimensions - e.g., performance, privacy, fairness, or efficiency - at a time,…
Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget
Minh Duc Bui, Fabian David Schmidt, Goran Glavaš +1
Compared to standard language model (LM) pretraining (i.e., from scratch), Knowledge Distillation (KD) entails an additional forward pass through a teacher model that is typically…