← Search

Timm Dill

2 accepted papers

2025

SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models

NAACL 2025long

Large Language Models (LLMs) reproduce and exacerbate the social biases present in their training data, and resources to quantify this issue are limited. While research has attempted to identify and mitigate such biases, most efforts have been concentrated around English, lagging the rapid advanceme…

Cited by 1SourcePDFScholar
2024

Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ

ACL 2024findings

Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. However, most LLMs today, and open LLMs in particular, are often intended for use in just English (e.g. Llama2, Mistral) or a small handful of high-resource languages (e.g. Mixtral, Qwen). Recen…