We ground discussion in the history and philosophy of science. What did it take for other fields to move from cataloging phenomena to predicting and controlling them? AI can learn from that playbook.
Stella Biderman
Post hoc analysis can certainly be useful, especially if you’re primarily concerned with the behavior of a specific deployed model. But looking at a static model will not tell you why the model developed a behavior. The real causal story must go back to the training process.
In film, "we'll fix it in post" is what you say when something went wrong on set and you don't want to redo it. AI research has made it our entire methodology: train the model, then patch whatever comes out. Our new ICML oral argues this can't be the basis of a science of AI. 🧵
Part of why post hoc analysis dominates: it's the only thing most researchers CAN do. Almost no one releases intermediate checkpoints or training data. we built MultiBERT and Pythia to set a better standard, and it's been great to see work like OLMo and Marin follow our lead.
A test for progress: a science of AI should support progressively stronger forms of understanding.
1. Predict outcomes from early training signals
2. Intervene to correct trajectories on undesirable paths
3. Design training procedures that reliably produce desired properties
Models are not static objects. They're snapshots of time-evolving processes shaped by data, objectives, architectures, and optimization. But most research treats them as fixed artifacts, analyzing behaviors after training instead of asking why they emerged.
Read the full paper: arxiv.org/abs/2606.06533 or come listen to our oral @icmlconf.bsky.social!
Huge thanks to my co-authors @aflah02101.bsky.social Niloofar @catherinearnett.bsky.social @fbarez.bsky.social @nsaphra.bsky.social
Stay tuned for a related workshop (hopefully) at NeurIPS too!
A common issue with position papers is that they leave the reader wondering “okay, but what should I actually do”? To address this we provide open problems on a wide variety of topics throughout to illustrate our perspectives and guide future research
