Benchmarks can be superficial, but model explanations and evaluations are fundamentally intertwined. What if we used interpretability as principled, scientific evaluation? If it met scientific standards? arxiv.org/abs/2605.05508 coming to EvalEval at ACL as oral 🧵 1/6
Who's Who of AI
Isabelle Lee
ml/nlp phding @ usc, currently visiting harvard, scientisting @ startup;
interpretability & training & reasoning
iglee.me
What they're sharing
Rigorous Interpretation Is a Form of Evaluation arxiv.org
Articles & links
Their network
In Isabelle Lee's orbit
Center = Isabelle Lee. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.