Follow
Michael Hanna
Michael Hanna
PhD Student, University of Amsterdam
Verified email at uva.nl - Homepage
Title
Cited by
Cited by
Year
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
M Hanna, O Liu, A Variengien
Advances in Neural Information Processing Systems 36, 2024
139*2024
A fine-grained analysis of BERTScore
M Hanna, O Bojar
Proceedings of the Sixth Conference on Machine Translation, 507-517, 2021
692021
Analyzing BERT’s knowledge of hypernymy via prompting
M Hanna, D Mareček
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting …, 2021
322021
Llms instead of human judges? a large scale empirical study across 20 nlp evaluation tasks
A Bavaresco, R Bernardi, L Bertolazzi, D Elliott, R Fernández, A Gatt, ...
arXiv preprint arXiv:2406.18403, 2024
312024
Identifying and adapting transformer-components responsible for gender bias in an english language model
A Chintam, R Beloch, W Zuidema, M Hanna, O Van Der Wal
Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting …, 2023
122023
Have faith in faithfulness: Going beyond circuit overlap when finding model mechanisms
M Hanna, S Pezzelle, Y Belinkov
First Conference on Language Modeling, 2024
92024
When language models fall in love: Animacy processing in transformer language models
M Hanna, Y Belinkov, S Pezzelle
Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023
92023
Transformer-specific Interpretability
H Mohebbi, J Jumelet, M Hanna, A Alishahi, W Zuidema
Proceedings of the 18th Conference of the European Chapter of the …, 2024
62024
LLM circuit analyses are consistent across training and scale
C Tigges, M Hanna, Q Yu, S Biderman
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
42024
ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation
J Jumelet, M Hanna, MDH Kloots, A Langedijk, C Pouw, O Van Der Wal
Proceedings of the BabyLM Challenge at the 27th Conference on Computational …, 2023
42023
The functional relevance of probed information: A case study
M Hanna, R Zamparelli, D Mareček
Proceedings of the 17th Conference of the European Chapter of the …, 2023
32023
Investigating Large Language Models' Representations Of Plurality Through Probing Interventions
M Hanna
Univerzita Karlova, Matematicko-fyzikální fakulta, 2022
32022
Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!
F Wildenburg, M Hanna, S Pezzelle
Findings of the Association for Computational Linguistics ACL 2024, 9598–9613, 2024
22024
ACT-thor: A controlled benchmark for embodied action understanding in simulated environments
M Hanna, F Pedeni, A Testoni, A Suglia, R Bernardi
Proceedings of the 29th International Conference on Computational …, 2022
22022
Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models
M Hanna, A Mueller
arXiv preprint arXiv:2412.05353, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–15