Publications
Sourati, Z., Liu, M. M., Wang, R., Wang, Z., Hu, Y., Guo, L., … & Roth, D. (2026). VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents. arXiv preprint arXiv:2610.20964. (Under review)
Sourati, Z., Liu, M. M., Wang, Z., Wang, R., Somayajula, S. A., Sheng, T., … & Roth, D. (2026). Same Context, Different Agents: A Behavioral Study of Semantic Layers, Orchestration and Compaction in Data Agents. arXiv preprint arXiv:2610.20959. (Under review)
Sourati, Z., Wu, M. H., Ghazizadeh, N., Kaplan, J., Dehghani, M., & Nastase, S. A. (2026). Cognitive Expert Language Models Better Align with the Corresponding Brain Systems. arXiv preprint arXiv:2609.36239. (Under review)
Sourati, Z., Karimi-Malekabadi, F., Ozcan, M., McDaniel, C., Ziabari, A., Trager, J., … & Dehghani, M. (2026). The Shrinking Landscape of Linguistic Diversity in the Age of Large Language Models. Nature Human Behaviour.
Sourati, Z., Ziabari, A. S., & Dehghani, M. (2026). The Homogenizing Effect of Large Language Models on Human Expression and Thought. Trends in Cognitive Sciences.
Sourati, Z., Wang, Z., Liu, M. M., Hu, Y., Guo, M., Bharadwaj, S., … & Roth, D. (2026). LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding. In Proceedings of ACL 2026 (Volume 1: Long Papers).
Golazizian, P., Rahmati, E., Trager, J., Sourati, Z., Ghazizadeh, N., Chochlakis, G., … & Dehghani, M. (2026). The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footage. In Proceedings of ACL 2026 (Volume 1: Long Papers).
Ziabari, A. S., Ghazizadeh, N., Sourati, Z., Karimi-Malekabadi, F., Piray, P., & Dehghani, M. (2026). Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking. (Accepted to COLM 2026)
Rahmati, E., Ghazizadeh, N., Sourati, Z., Rouhani, N., & Dehghani, M. (2026). Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training. arXiv preprint arXiv:2603.17198. (Under review)
Karimi-Malekabadi, F., Abdurahman, S., Sourati, Z., Trager, J., & Dehghani, M. (2026). Theory Trace Card: Theory-Driven Socio-Cognitive Evaluation of LLMs. arXiv preprint arXiv:2601.01878. (Under review)
Daryani, Y., Sourati, Z., & Dehghani, M. (2025). The Homogenizing Engine: AI’s Role in Standardizing Culture and the Path to Policy. Policy Insights from the Behavioral and Brain Sciences.
Ahrabian, K.*, Sourati, Z.*, Sun, K., Zhang, J., Jiang, Y., Morstatter, F., & Pujara, J. (2024). The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models. (Accepted to COLM 2024)
Jiang, Y., Zhang, J., Sun, K., Sourati, Z., Ahrabian, K., Ma, K., … & Pujara, J. (2024). MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning. (Accepted to NeurIPS 2024)
Sourati, Z., Ilievski, F., Sommerauer, P., & Jiang, Y. (2024). ARN: Analogical Reasoning on Narratives. Transactions of the Association for Computational Linguistics.
Deshpande, D., Sourati, Z., Ilievski, F., & Morstatter, F. (2024). Contextualizing Argument Quality Assessment with Relevant Knowledge. (Accepted to NAACL 2024)
Sourati, Z., Deshpande, D., Ilievski, F., Gashteovski, K., & Saralajew, S. (2024). Robust Text Classification: Analyzing Prototype-Based Networks. (Accepted to EMNLP 2024)
Jiang, Y., Ilievski, F., Ma, K., & Sourati, Z. (2023). BRAINTEASER: Lateral Thinking Puzzles for Large Language Models. (Accepted to EMNLP 2023)
Thakur, A. K., Ilievski, F., Sandlin, H. Â., Sourati, Z., Luceri, L., Tommasini, R., & Mermoud, A. (2023). Explainable Classification of Internet Memes. (Accepted to Nesy 2023)
Sourati, Z., Ilievski, F., Sandlin, H.-Â., & Mermoud, A. (2023). Case-based reasoning with language models for classification of logical fallacies. (Accepted to IJCAI 2023)
Sourati, Z., Venkatesh, V. P. P., Deshpande, D., Rawlani, H., Ilievski, F., Sandlin, H. Â., & Mermoud, A. (2023). Robust and explainable identification of logical fallacies in natural language arguments. (Accepted to Knowledge-Based Systems 2023)
Thakur, A., Ilievski, F., Sandlin, H., Mermoud, A., Sourati, Z., Luceri, L., & Tommasini, R. (2023). Multimodal and Explainable Internet Meme Classification. (Accepted in AI4SG-23 at AAAI-23)
ShabaniMirzaei, T., Chamani, H., Abaskohi, A., Sourati, Z., & Bahrak, B. (2023). A large-scale analysis of Persian Tweets regarding Covid-19 vaccination. (Accepted to Social Network Analysis and Mining 2023)
Sourati, Z., Sabri, N., Chamani, H., & Bahrak, B. (2022). Quantitative analysis of fanfictions’ popularity. (Accepted to Social Network Analysis and Mining 2022)
Setayesh, A., Sourati, Z., & Bahrak, B. (2022). Analysis of the global trade network using exponential random graph models. (Accepted to Applied Network Science 2022)
Sourati, Z., von Däniken, P., & Cieliebak, M. (2022). Ukraine–Russia: First insights into recent Twitter posts about this conflict. SwissText 2022 (Poster).
von Däniken, P., Sourati, Z., & Tuggener, D. (2022). Hateful Social Media Users – Can we predict their behavior? SwissText 2022 (Poster).
Chamani, H., Sourati, Z., & Bahrak, B. (2021). An Overview of Regression Methods in Early Prediction of Movie Ratings. In 2021 11th International Conference on Computer Engineering and Knowledge (ICCKE). IEEE.