Lukas Berglund

According to our database, Lukas Berglund authored at least 3 papers between 2023 and 2024.

Collaborative distances:

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

2024

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A".

Lukas Berglund, Meg Tong, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, Owain Evans

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Taken out of context: On measuring situational awareness in LLMs.

Lukas Berglund, Asa Cooper Stickland, Mikita Balesni, Maximilian Kaufmann, Meg Tong, Tomasz Korbak, Daniel Kokotajlo, Owain Evans

CoRR, 2023

Test Maintenance for Machine Learning Systems: A Case Study in the Automotive Industry.

Lukas Berglund, Tim Grube, Gregory Gay, Francisco Gomes de Oliveira Neto, Dimitrios Platis

Proceedings of the IEEE Conference on Software Testing, Verification and Validation, 2023