Lattice AI Research

Research focus

Eval Frameworks & Benchmarks (2)Code Generation & Program Synthesis (1)Red-Teaming & Adversarial Robustness (1)Data Curation & Synthetic Data (1)

Frequent co-authors

Adam Skurla (1)D. Macko (1)Martin Hyben (1)Martin Hyben (1)

Papers (2)

Apr 23, 2026

Adam Skurla +22d ago

mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code

Adapting machine-generated text detection methods to code proves competitive, but current LLMs still struggle to reliably identify AI-generated code, especially when obfuscated.

Adam Skurla, D. Macko, Jakub Simko

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Feb 18, 2026

MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models

Forget prompting: fine-tuning multilingual transformers on the new MultiCW dataset beats zero-shot LLMs at detecting check-worthy claims, even across languages and domains.

Martin Hyben, Martin Hyben, Sebastian Kula +8

Data Curation & Synthetic Data Eval Frameworks & Benchmarks Natural Language Processing

Search

Jakub Simko

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)