Papers by Daniel Braun

3 papers
AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts (2024.acl-long)

Copied to clipboard

Challenge: Annotated contracts are laborious task performed by companies, law firms, NGOs and the scientific community.
Approach: They present a corpus of 3,764 clauses from German consumer contracts annotated by legal experts with a clause in the contract.
Outcome: The proposed framework outperforms openly available models in detecting potentially void clauses.
Acquiescence Bias in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Acquiescence bias is a tendency of humans to agree with statements in surveys, independent of their actual beliefs.
Approach: They investigate the presence of acquiescence bias in Large Language Models across different models, tasks, and languages.
Outcome: The proposed model shows that LLMs display a bias towards answering no regardless of whether it indicates agreement or disagreement.
MucLex: A German Lexicon for Surface Realisation (2020.lrec-1)

Copied to clipboard

Challenge: lexica for rule-based surface realisers for languages other than English are often scarce.
Approach: They propose a German lexicon for the Natural Language Generation task of surface realisation based on the crowd-sourced online lexicont Wiktionary.
Outcome: The proposed lexicon contains more than 100,000 lemmata and 670,000 different word forms.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations