EVENTS

July 10, 2025 | Technische Universität Berlin, MAR building – MAR 4.033, 4th floor (Marchstr. 23, 10587 Berlin)

Lunch Talk: Robin Geyer - Measuring Orthogonality in Representations of Generative Models

In unsupervised representation learning, models aim to distill essential features from high-dimensional data into lower-dimensional learned representations, guided by inductive biases. Understanding the characteristics that make a good representation remains a topic of ongoing research. 

 

July 14, 2025 | TU Berlin Marchstr. 23, 10587 Berlin, MAR-Building, MAR 0.008

Measuring Political Bias in Large Language Models

The TU Berlin (NLP in Berlin / Emmy Noether series) invites you to this talk: Dr. Röttger will outline the challenges in evaluating political bias in LLMs and introduce IssueBench, a newly developed dataset designed for robust and realistic bias assessment.

772
44
34
*Data collected from 2020 onwards.

OPPORTUNITIES

BIFOLD welcomes job applications from interested parties year-round.

Image

PUBLICATIONS

Patrick Kahardipraja, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin

The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation

May 21, 2025
https://doi.org/10.48550/arXiv.2505.15807

Qianli Wang, Van Bach Nguyen, Nils Feldhus, Luis Felipe Villa-Arenas, Christin Seifert, Sebastian Möller, Vera Schmitt

Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals

May 20, 2025
https://doi.org/10.48550/arXiv.2505.13972

Qianli Wang, Mingyang Wang, Nils Feldhus, Simon Ostermann, Yuan Cao, Hinrich Schütze, Sebastian Möller, Vera Schmitt

Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability

May 20, 2025
https://doi.org/10.48550/arXiv.2505.13963

GRADUATE SCHOOL

Based on a highly competitive application process, the BIFOLD Graduate School offers an innovative fast-track PhD Program for students holding a bachelor’s degree, as well as a PhD Program for students with a master’s degree.

More info

INSTITUTIONAL PARTNERS

ASSOCIATED PARTNERS