pith. sign in

Batch calibration: Rethinking calibration for in-context learning and prompt engineering

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

2 Pith papers citing it

fields

cs.AI 1 cs.HC 1

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

From Words to Widgets for Controllable LLM Generation

cs.HC · 2026-04-13 · unverdicted · novelty 6.0

Malleable Prompting reifies subjective preferences from natural language into GUI widgets and modulates LLM token probabilities during decoding to enable controllable generation, with a user study showing improved precision and perceived controllability over standard prompting.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • From Words to Widgets for Controllable LLM Generation cs.HC · 2026-04-13 · unverdicted · none · ref 59

    Malleable Prompting reifies subjective preferences from natural language into GUI widgets and modulates LLM token probabilities during decoding to enable controllable generation, with a user study showing improved precision and perceived controllability over standard prompting.

  • Harnessing non-adversarial robustness in large language models cs.AI · 2026-05-28 · unverdicted · none · ref 25

    Debiasing via fine-tuning can enhance LLM robustness to semantically neutral prompt perturbations by addressing perturbation-induced bias in neural network outputs.