George Mihaila

According to our database, George Mihaila authored at least 5 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Learning to Explain: Supervised Token Attribution from Transformer Attention Patterns.

George Mihaila

CoRR, January, 2026

LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Text.

George Mihaila, Suleyman Olcay Polat, Poli Nemkova, Himanshu Sharma, Namratha V. Urs, Mark V. Albert

CoRR, January, 2026

2025

Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts.

Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2021

The first fine-resolution mapping of contour-levee irrigation using deep Bi-Stream convolutional neural networks.

Lu Liang, Abolfazl Meyarian, Xiaohui Yuan, Benjamin R. K. Runkle, George Mihaila, Yuchu Qin, Jacob Daniels, Michele L. Reba, James R. Rigby

Int. J. Appl. Earth Obs. Geoinformation, 2021

2020

Identifying FinTech Innovations Using BERT.

Doina Caragea, Mark Chen, Theodor Cojoianu, Mihai Dobri, Kyle Glandt, George Mihaila

Proceedings of the 2020 IEEE International Conference on Big Data (IEEE BigData 2020), 2020