Vera Neplenbroek
5 papers · 2025–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (2) 🗺️ Taxonomy Completionist (13)
🐝
Cross-Pollinator
(13)
👥
Mega-Team
(20)
❓
The Questioner
Conferences
ACL (4)
EMNLP (1)
Top co-authors
Keywords
large language model
(3)
bias mitigation
(2)
cross-lingual transfer
(1)
model evaluation
(1)
text generation
(1)
preference optimization
(1)
toxicity detection
(1)
language model evaluation
(1)
human judgment
(1)
prompt variation
(1)
human evaluation
(1)
faithful explanation
(1)
multilingual model
(1)
stereotype detection
(1)
nlp evaluation
(1)
model assessment
(1)
model bia
(1)
toxicity mitigation
(1)
interpretable concept
(1)
stereotype bia
(1)
Papers
One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization
ACL 2026
Actionable Interpretability for Churn Classification: A Text Bottleneck Model Case Study at a Major Telecom Provider
ACL 2026
LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks
ACL 2025
Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
ACL 2025
Reading Between the Prompts: How Stereotypes Shape LLM’s Implicit Personalization
EMNLP 2025