Florian Schottmann — accepted AI-conference papers

2024

Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?

Tannon Kew, Florian Schottmann, Rico Sennrich

EMNLP 2024finding

The vast majority of today’s large language models (LLMs) are English-centric, having been pretrained predominantly on English text. Yet, in order to meet user expectations, models need to be able to respond appropriately in multiple languages once deployed in downstream applications. This requires…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗

2023

Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model

Chantal Amrhein, Florian Schottmann, Rico Sennrich, Samuel Läubli

ACL 2023long

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more gender-fair language by creating pseudo training data throu…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗