Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

We Can't Understand AI Using our Existing Vocabulary

cs.CL · 2025-02-11 · conditional · novelty 4.0

AI interpretability is reframed as building a shared human-machine language in which each new word is a learned token embedding trained by preference optimization.

citing papers explorer

Showing 1 of 1 citing paper.

  • We Can't Understand AI Using our Existing Vocabulary cs.CL · 2025-02-11 · conditional · none · ref 5

    AI interpretability is reframed as building a shared human-machine language in which each new word is a learned token embedding trained by preference optimization.