Aleksandra Bakalova

According to our database, Aleksandra Bakalova authored at least 6 papers between 2024 and 2026.

Collaborative distances:

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

2026

How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning.

Entang Wang, Yiwei Wang, Aleksandra Bakalova, Michael Hahn

CoRR, May, 2026

Discovering Interpretable Algorithms by Decompiling Transformers to RASP.

Xinting Huang, Aleksandra Bakalova, Satwik Bhattamishra, William Merrill, Michael Hahn

CoRR, February, 2026

2025

Born a Transformer - Always a Transformer?

Yana Veitsman, Mayank Jobanputra, Yash Raj Sarrof, Aleksandra Bakalova, Vera Demberg, Ellie Pavlick, Michael Hahn

CoRR, May, 2025

Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B.

Aleksandra Bakalova, Yana Veitsman, Xinting Huang, Michael Hahn

CoRR, April, 2025

Born a Transformer - Always a Transformer? On the Effect of Pretraining on Architectural Abilities.

Mayank Jobanputra, Yana Veitsman, Yash Raj Sarrof, Aleksandra Bakalova, Vera Demberg, Ellie Pavlick, Michael Hahn

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

2024

LUNA: A Framework for Language Understanding and Naturalness Assessment.

Marat Saidov, Aleksandra Bakalova, Ekaterina Taktasheva, Vladislav Mikhailov, Ekaterina Artemova

CoRR, 2024