Please see my Google Scholar page for an up-to-date list.
2026
Nikas, T., Subramani, N., & Mueller, A. (2026). “Improving Confidence Estimation in Language Models with Linear Representations of Ambiguity.” In Actionable Interpretability @ COLM 2026. Under review at ARR. [arXiv]
Tzimas, S., Nikas, T., Pitoura, E., & Tsaparas, P. (2026). “Minimizing the Cost of PageRank Fairness.” In WebGraph @ WSDM 2026. [PDF]
2025
Calais, P., Franco, G., Tang, Z., Nikas, T., Meira Jr., W., Terzi, E., & Crovella, M. (2025). “Disentangling Text and Math in Word Problems: Evidence for the Bidimensional Structure of Large Language Models’ Reasoning.” In Findings of ACL 2025. [ACL Anthology]
Calais, P., Franco, G., Nikas, T., Tang, Z., Crovella, M., Meira Jr., W., & Terzi, E. (2025). “Beyond Accuracy: Understanding the Performance of LLMs on Exams Designed for Humans.” Preprint. [PDF]