I am a final-year PhD student in Computational Linguistics and Cognitive Science at the University of Zurich, working in the Digital Linguistics Lab under the supervision ofProf. Dr. Lena A. Jäger and Prof. Dr. Rico Sennrich. 

My research lies at the intersection of human language processing and NLP, with a focus on reliability and robustness both in LLMs and human language processing. I am particularly interested in evaluating biases in LLMs (e.g., political bias) and examining how robust these biases are across different conditions, including prompt variation and out-of-distribution inputs. On the human side, my work explores the reliability of individual differences in language processing, especially during reading, using methods such as eye-tracking and self-paced reading.

I previously completed a research scientist internship in the FAIR Alignment team at Meta London, where I worked with Sam Bell on assessing robustness of probing techniques used in interpretability research. A preprint of our work can be found here. I am currently a Research Scientist Intern at Google Munich (through December 2026), working on memorization in LLMs.

Previously, I obtained my Master’s degree in Neural Systems and Computation from ETH Zurich, conducting my thesis research at the Developmental Neuroimaging group (Department of Child and Adolescent Psychiatry). I also hold a Bachelor's degree in Comparative Linguistics (Indo-European and General Linguistics) and Neuroinformatics from the University of Zurich.

Replicate me if you can: Assessing measurement reliability of individual differences in reading across measurement occasions and methods, Cognitive Science
Patrick Haller, Cui Ding, Maja Stegenwallner-Schütz, David R. Reich, Iva Koncic, Silvia Makowski and Lena A. Jäger
[http |bib]

LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance, under review
Patrick Haller, Mark Ibrahim, Polina Kirichenko, Levent Sagun, Samuel J. Bell
[http ]

Leveraging In-Context Learning for Political Bias Testing of LLMs, ACL 2025
Patrick Haller, Jannis Vamvas, Rico Sennrich and Lena A. Jäger
[http |bib ]

Proxy-Based Pre-Training for Eye-Tracking Applications,  ETRA 2025
David R. Reich, Cui Ding, Lena S. Bolliger, Patrick Haller, Paul Prasse, Lena A. Jäger
[http |pdf  |bib]

Neural representations of association strength and prediction error during novel symbol-speech sounds learning, Imaging Neuroscience, 01/2025
Gorka Fraga-González, Patrick Haller, David Willinger, Vanessa Gehrig, Nada Frei, Silvia Brem
[http | bib]

On the alignment of LM language generation and human language comprehension,  BlackboxNLP 2024
Lena S. Bolliger, Patrick Haller, Lena A. Jäger
[ http |bib]

EMTeC: A Corpus of Eye Movements on Machine-Generated Texts,  Behavior Research Methods
Lena S. Bolliger, Patrick Haller, Isabelle C. R. Cretton, David R. Reich, Tannon Kew,  Lena A. Jäger
[http |data |bib]

Yes, no, maybe? Revisiting language models' response stability under paraphrasing for the assessment of political leaning, COLM 2024
Patrick Haller, Jannis Vamvas, and Lena A. Jäger
[http |pdf |bib]

Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences, ACL 2024
Patrick Haller, Lena S. Bolliger, and Lena A. Jäger
[http |pdf | bib]

On language models’ cognitive biases in reading time prediction, ICML workshop on Large Language Models and Cognition 2024
Patrick Haller, Lena S. Bolliger, and Lena A. Jäger
[http |pdf | bib]

Towards a mechanistic understanding of reading difficulties: Deviant audiovisual learning dynamics and network connectivity in children with poor reading skills, accepted to Journal of Neuroscience, 2025
Nada Frei, David Willinger, Patrick Haller, Gorka Fraga-González, Gustavo Pamplona, Amelie Haugg, Christina Lutz, Seline Coraj, Eva Hefti, and Silvia Brem 

PoTeC: A German Naturalistic Eye-tracking-while-reading Corpus, Behavior Research Methods 2025
Deborah N. Jakobi, Thomas Kern, David R. Reich, Patrick Haller, and Lena A. Jäger
[http |code | bib]

Digital comprehensibility assessment of simplified texts among persons with intellectual disabilities, CHI 2024
Andreas Säuberli, Franz Holzknecht, Patrick Haller, Silvana Deilen, Laura Schiffl, Silvia Hansen-Schirra, and Sarah Ebling
[http | bib]

ScanDL: A Diffusion Model for Generating Synthetic Scanpaths on Texts,  EMNLP 2023
Lena S. Bolliger, David R. Reich, Patrick Haller, Deborah N. Jakobi, Paul Prasse, Lena A. Jäger
[ http |Video |Poster |bib]

Eyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading, ETRA 2023
Shuwen Deng, David R. Reich, Paul Prasse, Patrick Haller, Tobias Scheffer and Lena A. Jäger
[http |bib | code]

Eye-tracking based classification of Mandarin Chinese readers with and without Dyslexia, EMNLP/TSAR 2022
Patrick Haller, Andreas Säuberli, Sarah Elisabeth Kiener, Jinger Pan, Ming Yan, and Lena A. Jäger
[http | bib]

Measurement Reliability of Individual Differences in Sentence Processing, AMLaP 2022
Patrick Haller, Iva Koncic, David R. Reich, Chiara Tschirner, Silvia Makowski, and Lena A. Jäger
[pdf]

Inferring Reading Comprehension from Eye Movements, poster presented at AMLaP 2022
David R. Reich, Paul Prasse, Chiara Tschirner, Patrick Haller, Maja Stegenwallner-Schütz, Frank Goldhammer, and Lena A. Jäger
[poster]

Inferring Native and Non-Native Human Reading Comprehension and Subjective Text Difficulty from Scanpaths in Reading, ETRA 2022
David R. Reich, Paul Prasse, Chiara Tschirner, Patrick Haller, Frank Goldhammer, and Lena A. Jäger
[http | bib]

Revisiting the Uniform Information Density Hypothesis, EMNLP 2021
Clara Meister, Tiago Pimentel, Patrick Haller, Lena Jäger, Ryan Cotterell and Roger Levy
[ http | bib]

Potsdam Textbook Corpus (PoTeC), OSF
Lena Jäger, Thomas Kern and Patrick Haller
[http]