Samuel Albanie

Samuel Albanie

Preparing for AI R&D Automation: Scalable Oversight and Hard Benchmarks.

A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility

Andreas Hochlehnert and Hardik Bhatnagar and Vishaal Udandarao and Samuel Albanie and Ameya Prabhu and Matthias Bethge, arXiv preprint arXiv:2504.07086, 2025
paper

@article{hochlehnert2025sober,
    author = "Hochlehnert, Andreas and Bhatnagar, Hardik and Udandarao, Vishaal and Albanie, Samuel and Prabhu, Ameya and Bethge, Matthias",
    title = "A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility",
    year = "2025",
    month = "April",
    journal = "arXiv preprint arXiv:2504.07086"
}