Follow
Mansi Sakarvadia
Mansi Sakarvadia
Computer Science Ph.D. Student, University of Chicago
Verified email at uchicago.edu - Homepage
Title
Cited by
Cited by
Year
Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models
M Sakarvadia, A Ajith, A Khan, D Grzenda, N Hudson, A Bauer, K Chard, ...
BlackboxNLP Workshop at EMNLP 2023, 2023
182023
Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism
M Sakarvadia, A Khan, A Ajith, D Grzenda, N Hudson, A Bauer, K Chard, ...
Attributing Model Behavior at Scale Workshop in NeurIPS 2023, 2023
132023
Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision
N Hudson, JG Pauloski, M Baughman, A Kamatar, M Sakarvadia, L Ward, ...
In IEEE/ACM International Conference on Big Data Computing, Applications and …, 2024
62024
Lazy python dependency management in large-scale systems
A Kamatar, M Sakarvadia, V Hayot-Sasson, K Chard, I Foster
2023 IEEE 19th International Conference on e-Science (e-Science), 1-10, 2023
42023
Sok: On finding common ground in loss landscapes using deep model merging techniques
A Khan, T Nief, N Hudson, M Sakarvadia, D Grzenda, A Ajith, J Pettyjohn, ...
arXiv preprint arXiv:2410.12927, 2024
22024
Mitigating memorization in language models
M Sakarvadia, A Ajith, A Khan, N Hudson, C Geniesse, K Chard, Y Yang, ...
ICLR 2025, 2024
12024
Ecological functions and ecosystem services of overwash ponds on North Core banks, NC
S Cadell, Y Chen, J Daly, J Evans, C Herschfield, J Hynes, P Lim, ...
12021
Toward Non-Invasive Diagnosis of Bankart Lesions with Deep Learning
S Sethi, S Reddy, M Sakarvadia, J Serotte, D Nwaudo, N Maassen, L Shi
arXiv preprint arXiv:2412.06717, 2024
2024
Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning
M Sakarvadia
arXiv preprint arXiv:2411.05037, 2024
2024
De Bello Homomorphico: Investigation of the extensibility of the OpenFHE library with basic mathematical functions by means of common approaches using the example of the CKKS …
T Prantl, L Horn, S Engel, L Iffländer, L Beierlieb, C Krupitzer, A Bauer, ...
International Journal of Information Security 23 (2), 1149-1169, 2024
2024
Mind Your Manners: Detoxifying Language Models
J Pettyjohn, N Hudson, M Sakarvadia, A Ajith, K Chard
Mind Your Manners: Detoxifying Language Models via Attention Head Intervention
JN Pettyjohn, NC Hudson, M Sakarvadia, A Ajith, K Chard
The 7th BlackboxNLP Workshop, 0
Atypical Neonate Extra-axial CSF is Associated with Reduced Cognitive Development at Age 1 and 2
M Sakarvadia, R Li, SH Kim, V Murphy, E Cornea, JC Prieto, M Shen, ...
The system can't perform the operation now. Try again later.
Articles 1–13