collaborators

7 papers

cs.CL2026

Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts

Arthur Wuhrmann, Gaetan Stein, Daniel Brunner +1

While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigated…

cs.AI2026

LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context

Anastasiia Kucherenko, François Brouchoud, Dimitri Percia David +1

While the validity of LLMs' use in the legal context remains subject to ethical and legal debate, legal professionals are already experimenting with personal LLMs, if only for tran…

cs.CR2026

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic

LLM-based coding assistants are seeing rapid adoption, offering substantial gains in developer productivity. As organizations increasingly ship code these agents produce, the secur…

cs.CL2025

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Project Apertus, Alejandro Hernández-Cano, Alexander Hägele +100

We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingu…

cs.CL2025

Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World

Ines Altemir Marinas, Anastasiia Kucherenko, Alexander Sternfeld +1

The performance of Large Language Models (LLMs) is determined by their training data. Despite the proliferation of open-weight LLMs, access to LLM training data has remained limite…

cs.CL2025

Going over Fine Web with a Fine-Tooth Comb: Technical Report of Indexing Fine Web for Problematic Content Search and Retrieval

Inés Altemir Marinas, Anastasiia Kucherenko, Andrei Kucharavy

Large language models (LLMs) rely heavily on web-scale datasets like Common Crawl, which provides over 80\% of training data for some modern models. However, the indiscriminate nat…