pith. sign in

Training language models to follow in- structions with human feedback

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

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation

cs.AI · 2026-05-17 · unverdicted · novelty 7.0

VLA driving models exhibit only 42.5% reasoning fidelity, miss pedestrians frequently, show 97.7% trajectory fragility to mild perturbations, and display low reasoning-action consistency in nearly half of cases.

citing papers explorer

Showing 1 of 1 citing paper.

  • Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation cs.AI · 2026-05-17 · unverdicted · none · ref 9

    VLA driving models exhibit only 42.5% reasoning fidelity, miss pedestrians frequently, show 97.7% trajectory fragility to mild perturbations, and display low reasoning-action consistency in nearly half of cases.