Marlies Hafer

Marlies Hafer

Auto-generated profile, based on publicly available information

Marlies Hafer

TU Dortmund University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 October 2025
Verified
Book Chapter
Open access
PDF file
IDIna Dormuth
Ina Dormuth
SFSven Franke
Sven Franke
MHMarlies Hafer
Marlies Hafer
TKTim Katzke
Tim Katzke
AMAlexander Marx
Alexander Marx
JRJérôme Rutinowski
Jérôme Rutinowski
This study examines the reliability of AI-based Voting Advice Applications (VAAs) and large language models (LLMs) in providing objective political information. Our analysis is based upon comparing party responses to 38 statements of the Wahl-O-Mat, a well-established German online tool that helps inform voters by comparing their views with political party positions. For the LLMs, we identify significant biases. They exhibit a strong alignment (over 75% on average) with left-wing parties and a substantially lower alignment with center-right (smaller 50%) and right-wing parties (around 30%). Furthermore, for the VAAs, intended to objectively inform voters, we found substantial deviations from the parties’ stated positions in Wahl-O-Mat: While one VAA deviated in 25% of cases, another VAA showed deviations in more than 50% of cases. For the latter, we even observed that simple prompt injections led to severe hallucinations, including false claims such as non-existent connections between political parties and right-wing extremist ties.

6 May 2026 in Machine Learning
Verified
Journal Article
Open access
MHMarlies Hafer
Marlies Hafer
AMAlexander Marx
Alexander Marx
We consider the problem of estimating the expected causal effect $$E[Y|do(X)]$$ for a target variable $$Y$$ when treatment $$X$$ is set by intervention, focusing on continuous random variables. In settings without selection bias or confounding, $$E[Y|do(X)] = E[Y|X]$$ , which can be estimated using standard regression methods. However, regression fails when systematic missingness induced by selection bias, or confounding distorts the data. Proxy variables unaffected by the selection process can, under certain constraints, be used to correct for selection bias to recover $$E[Y|X]$$ , and hence $$E[Y|do(X)]$$ , reliably. When data is additionally affected by confounding, recovering the causal effect from selection-biased data is more challenging and requires access to proxies to both correct for confounding and for the selection mechanism. Assuming access to such proxies from external unbiased observational data, we derive theoretical conditions ensuring identifiability and recoverability of causal effects. We further introduce a linear two-step regression estimator (TSR), which can be extended through adding non-linear basis functions, capable of exploiting proxy variables to adjust for selection bias while accounting for confounding. We show that TSR is consistent with previous estimators when confounding is absent, but achieves a lower variance. Extensive simulation studies validate TSR’s correctness for scenarios that include both selection bias and confounding with proxy variables.