Recent posts

The Joy of Multiple-Choice

Box-ticking exams save ink and time.

Read post

OpenAI's Speculative Decoding,
Reverse-Engineered

Why LLMs are faster if we give them a draft to complete.

Read post

An Encoder Model for Swiss German

SwissBERT can now process written Swiss German.

Read post

Wenn ChatGPT den Smartvote-Fragebogen ausfüllt

Sind Sprachmodelle politisch voreingenommen?

Read post

View All Posts

Recent publications

Jannis Vamvas, Ignacio Pérez Prat, Angela Heldstab, Dominic P. Fischer, Sina Ahmadi and Rico Sennrich. 2026. Translation Asymmetry in LLMs as a Data Augmentation Factor: A Case Study for 6 Romansh Language Varieties. Pre-print. [cite] [data] [model] [code]

Charlotte Model, Sina Ahmadi and Jannis Vamvas. 2026. Robust Language Identification for Romansh Varieties. Pre-print. [cite] [code]

Michelle Wastl, Jannis Vamvas and Rico Sennrich. 2025. SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents. Pre-print. [cite] [data] [code]

Jannis Vamvas, Ignacio Pérez Prat, Not Battesta Soliva, and 14 others. 2025. Expanding the WMT24++ Benchmark with Rumantsch Grischun, Sursilvan, Sutsilvan, Surmiran, Puter, and Vallader. In Proceedings of the Tenth Conference on Machine Translation (WMT 2025), pages 1028–1047, Suzhou, China. Association for Computational Linguistics. [cite] [data] [code]

Hanxu Hu, Jannis Vamvas and Rico Sennrich. 2025. Source-primed Multi-turn Conversation Helps Large Language Models Translate Documents. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 23702–23712, Suzhou, China. Association for Computational Linguistics. [cite] [code]

View All Publications

Recent teaching

View all classes taught