19 papers
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…
Mitigating Label Length Bias in Large Language Models
Mario Sanz-Guerrero, Katharina von der Wense
Large language models (LLMs) are powerful zero- and few-shot learners. However, when predicting over a set of candidate options, LLMs suffer from label biases, and existing calibra…
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…