Syeda Mahwish — accepted AI-conference papers

2025

Capturing Human Cognitive Styles with Language: Towards an Experimental Evaluation Paradigm

Vasudha Varadarajan, Syeda Mahwish, Xiaoran Liu, Julia Buffolino, Christian Luhmann, Ryan L. Boyd +1

NAACL 2025short

While NLP models often seek to capture cognitive states via language, the validity of predicted states is determined by comparing them to annotations created without access the cognitive states of the authors. In behavioral sciences, cognitive states are instead measured via experiments. Here, we in…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Systematic Evaluation of Auto-Encoding and Large Language Model Representations for Capturing Author States and Traits

Khushboo Singh, Vasudha Varadarajan, Adithya V. Ganesan, August Håkan Nilsson, Nikita Soni, Syeda Mahwish +5

ACL 2025finding

Large Language Models (LLMs) are increasingly used in human-centered applications, yet their ability to model diverse psychological constructs is not well understood. In this study, we systematically evaluate a range of Transformer-LMs to predict psychological variables across five major dimensions:…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge

Vasudha Varadarajan, Swanie Juhng, Syeda Mahwish, Xiaoran Liu, Jonah Luby, Christian Luhmann +1

ACL 2023long

While transformer-based systems have enabled greater accuracies with fewer training examples, data acquisition obstacles still persist for rare-class tasks – when the class label is very infrequent (e.g. < 5% of samples). Active learning has in general been proposed to alleviate such challenges, but…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗