Scholar
Geetanjali Bihani
Google Scholar ID: ecIkwcUAAAAJ
Purdue University
Citations & Impact
Citations
79
H-index
5
i10-index
2
Publications
15
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- March 2025 - Received A.H. Ismail Interdisciplinary Graduate Degree Grant from Purdue University! March 2025 - Received Graduate Student Travel Grant from Purdue Polytechnic Institute! January 2025 - Delivered an ignite talk, “Bridging the Gap: Advancing AI for Detecting Covert Online Harms,” in the Digital and Social Media Track at HICSS-58. December 2024 - Paper on “Examining Language Model’s Behavior with Occupation Attributes” accepted to COLING 2025. August 2024 - Paper on “The Reliability Paradox: Exploring How Shortcut Learning Undermines Language Model Calibration” accepted to HICSS-58.
Research Experience
- During her PhD, she explored a range of challenges in language model reasoning, including quantifying how alignment methods exacerbate opposing biases, demonstrating that calibrated models lack generalizability, developing methods for sense-enrichment of contextualized representations, and working on fuzzy models for intent classification, including task-based intent as well as covert malicious intents.
Education
- PhD Candidate at Purdue University, working under Dr. Julia Taylor Rayz in the AKRaNLU Lab.
Background
- A researcher in Natural Language Understanding, focusing on enhancing the reasoning capabilities of language models by addressing linguistic ambiguity and improving generalization, especially in cases where the structural form (locution) differs from the intended communicative function (illocution), as often seen in manipulative discourse.
Miscellany
- For more information regarding her work, please check out her Google Scholar page.
Co-authors