565 citations · 568 across the 2 of their papers we have counts for
3 papers
Tracing the Representation Geometry of Language Models from Pretraining to Post-training
Melody Zixuan Li, Kumar Krishna Agrawal, Arna Ghosh +4
Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral approach to investigate the geometry of learn…
Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
Kaitlyn Zhou, Jena D. Hwang, Xiang Ren +3
The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models. However, current evaluations of these abilities rely on simple cali…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…