I am a PhD candidate in the Digital Linguistics group, supervised by Prof. Dr. Lena A. Jäger and Prof. Dr. Rico Sennrich. Conducting research at the intersection of NLP and cognitive science, I am working on creating innovative solutions that enhance language model performance and interpretability. Currently, my research focusses on the cognitive alignment in language models and on diffusion models for synthetic eye movement generation.
From July 2025 to January 2026, I worked a Research Intern at Huawei London in the NLP Research Group, where I worked on improving LLMs' language understanding by inserting dynamic latent tokens.
Preprints
Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization, preprint
Lena S. Bolliger and Lena A. Jäger
[arXiv preprint | bib ]
Publications
ZORA Publication List
Download Options
Publications
-
Eye-tracking-while-reading: A living survey of datasets with open library support Behavior Research Methods, 58, 263. https://doi.org/10.3758/s13428-026-03126-6
-
A Benchmark for Deep Information Synthesis (B. Hariharan, A. Faust, D. Yang, C. Raffel, & L. Pinto, Eds.; p. online). s.n. https://proceedings.iclr.cc/paper_files/paper/2026/file/6b8c452854757ef263007bdac4096733-Paper-Conference.pdf
-
Genre Matters: How Text Types Interact with Decoding Strategies and Lexical Predictors in Shaping Reading Behavior (C. Christodoulopoulos, T. Chakraborty, C. Rose, & V. Peng, Eds.; pp. 7470–7487). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.emnlp-main.379
-
Wave 2 of the Multilingual Eye-Movement Corpus (MECO): New text reading data across languages Scientific Data, 12, 1183. https://doi.org/10.1038/s41597-025-05453-3
-
EMTeC: A Corpus of Eye Movements on Machine-Generated Texts Behavior Research Methods, 57, 189. https://doi.org/10.3758/s13428-025-02677-4
-
Proxy-Based Pre-Training for Eye-Tracking Applications (Y. Sugano, M. Khamis, A. Chetouani, L. Sidenmark, & A. Bruno, Eds.; p. 26). ACM Digital library. https://doi.org/10.1145/3715669.3723113
-
ScanDL 2.0: A Generative Model of Eye Movements in Reading Synthesizing Scanpaths and Fixation Durations Proceedings of the ACM on Human-Computer Interaction, 9, ETRA05. https://doi.org/10.1145/3725830
-
New data on text reading in English as a second language: The Wave 2 expansion of the Multilingual Eye-Movement Corpus (MECO) Studies in Second Language Acquisition, 47, 677–695. https://doi.org/10.1017/S0272263125000105
-
On the alignment of LM language generation and human language comprehension 217–231. https://doi.org/10.18653/v1/2024.blackboxnlp-1.14
-
Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences (No. 62). 7878–7892. https://doi.org/10.18653/v1/2024.findings-acl.469
-
An Eye Opener Regarding Task-Based Text Gradient Saliency (T. Kuribayashi, G. Rambelli, E. Takmaz, & et al, Eds.; pp. 255–263). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.cmcl-1.22
-
On language models’ cognitive biases in reading time prediction online. https://openreview.net/forum?id=io5QAglkER
-
ScanDL: A Diffusion Model for Generating Synthetic Scanpaths on Texts (H. Bouamor, J. Pino, & K. Bali, Eds.; pp. 15513–15538). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.960
Talks
Introducing ScanDL: A diffusion-based generative model of eye movements in reading, MathPsych/ICCM 2024 (Society for Mathematical Psychology and International Conference on Cognitive Modeling)
Lena S. Bolliger, David R. Reich, Patrick Haller, Deborah N. Jakobi, Paul Prasse, Lena A. Jäger
Teaching
| Semester |
Course |
|---|---|
| HS 2025 | Lecturer in Mathematics for Computational Linguistics 2 |
| HS 2024 | Lecturer in Mathematics for Computational Linguistics 2 |
| HS 2024 | Lecturer in Cognitively Enhanced NLP |
|
HS 2023 |
Lecturer in Cognitively Enhanced NLP |
| HS 2022 | TA in Quantitative Methods |
| FS 2022 | TA in Eye tracking: Experiment design and machine learning methods |
| HS 2021 |
TA in Quantitative Methods |