3 papers
cs.AI2026
Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
Stella Biderman, Mohammad Aflah Khan, Niloofar Mireshghallah +3
What would it mean to have a scientific understanding of AI? Models are not static objects: they are snapshots of time-evolving processes shaped by data, objectives, architectures,…
cs.LG2025
Using Shapley interactions to understand how models use structure
Divyansh Singhvi, Diganta Misra, Andrej Erkelens +3
Language is an intricately structured system, and a key goal of NLP interpretability is to provide methodological insights for understanding how language models represent this stru…
cs.SE2024
Benchmarks as Microscopes: A Call for Model Metrology
Michael Saxon, Ari Holtzman, Peter West +2
Modern language models (LMs) pose a new challenge in capability assessment. Static benchmarks inevitably saturate without providing confidence in the deployment tolerances of LM-ba…