Michael Hanna

According to our database, Michael Hanna authored at least 10 papers between 2021 and 2024.

Collaborative distances:

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

2024

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms.

Michael Hanna, Sandro Pezzelle, Yonatan Belinkov

CoRR, 2024

Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!

Frank Wildenburg, Michael Hanna, Sandro Pezzelle

CoRR, 2024

2023

ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation.

Jaap Jumelet, Michael Hanna, Marianne de Heer Kloots, Anna Langedijk, Charlotte Pouw, Oskar van der Wal

CoRR, 2023

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.

Michael Hanna, Ollie Liu, Alexandre Variengien

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

When Language Models Fall in Love: Animacy Processing in Transformer Language Models.

Michael Hanna, Yonatan Belinkov, Sandro Pezzelle

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

The Functional Relevance of Probed Information: A Case Study.

Michael Hanna, Roberto Zamparelli, David Marecek

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model.

Abhijith Chintam, Rahel Beloch, Willem H. Zuidema, Michael Hanna, Oskar van der Wal

Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, 2023

2022

ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments.

Michael Hanna, Federico Pedeni, Alessandro Suglia, Alberto Testoni, Raffaella Bernardi

Proceedings of the 29th International Conference on Computational Linguistics, 2022

2021

A Fine-Grained Analysis of BERTScore.

Michael Hanna, Ondrej Bojar

Proceedings of the Sixth Conference on Machine Translation, 2021

Analyzing BERT's Knowledge of Hypernymy via Prompting.

Michael Hanna, David Marecek

Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2021