pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

Fuzzing Large Language Models to Elicit Hidden Behaviours

cs.LG · 2026-06-28 · unverdicted · novelty 7.0

Fuzzing via Gaussian noise on weights or residual activations elicits hidden backdoor behaviors more often than temperature sampling on four of six models, with proxy-task hyperparameter selection via Thompson sampling improving results over uniform sweeps.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Fuzzing Large Language Models to Elicit Hidden Behaviours cs.LG · 2026-06-28 · unverdicted · none · ref 6

    Fuzzing via Gaussian noise on weights or residual activations elicits hidden backdoor behaviors more often than temperature sampling on four of six models, with proxy-task hyperparameter selection via Thompson sampling improving results over uniform sweeps.