Kevin Meng

1100

550

275

825

20212022202320244 52 378 1015

Public access

2 articles

0 articles

available

not available

Based on funding mandates

David BauAssistant Professor at Northeastern UniversityVerified email at northeastern.edu
Yonatan BelinkovTechnionVerified email at technion.ac.il
Alex AndonianPhD in EECS, MITVerified email at mit.edu
Arnab Sen SharmaPh.D. student at Northeastern UniversityVerified email at sust.edu
Chengkai LiProfessor of Computer Science and Engineering, The University of Texas at ArlingtonVerified email at uta.edu
Evan HernandezGraduate Student, MITVerified email at mit.edu
Martin WattenbergHarvard University / Google ResearchVerified email at seas.harvard.edu
Jacob AndreasMITVerified email at mit.edu
Jagdeep Singh BhatiaMassachusetts Institute of TechnologyVerified email at mit.edu

Kevin Meng

Verified email at csail.mit.edu - Homepage


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Locating and Editing Factual Associations in GPT K Meng, D Bau, A Andonian, Y Belinkov 36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022	987	2022
Mass-Editing Memory in a Transformer K Meng, AS Sharma, A Andonian, Y Belinkov, D Bau 11th International Conference on Learning Representations (ICLR 2023), 2022	407	2022
Linearity of relation decoding in transformer language models E Hernandez, AS Sharma, T Haklay, K Meng, M Wattenberg, J Andreas, ... 12th International Conference on Learning Representations (ICLR 2024), 2023	49	2023
Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims K Meng, D Jimenez, F Arslan, JD Devasier, D Obembe, C Li Under review in ACM Transactions, 2020	17	2020
A Dashboard for Mitigating the COVID-19 Misinfodemic Z Zhu, K Meng, J Caraballo, I Jaradat, X Shi, Z Zhang, F Akrami, H Liao, ... 16th Conference of the European Association for Computational Linguistics …, 2021	6	2021
Exploiting and Defending Against the Approximate Linearity of Apple’s NeuralHash JS Bhatia, K Meng ICML 2022 Workshop on Cybersecurity, 2022	3	2022
Interpreting and Editing Memory in Large Transformer Language Models K Meng Massachusetts Institute of Technology, 2024		2024
An End-to-End Computational System for Monitoring and Verifying Factual Claims K Meng NeurIPS 2021 Workshop on AI for Credible Elections, 2021		2021

The system can't perform the operation now. Try again later.

Articles 1–8

Citations per year