A hybrid fine-tuning objective using KL divergence for token calibration and Kahneman-Tversky optimization for semantic binding enables LLMs to produce outputs that match desired attribute distributions across repeated prompts.
RLP rompt: Optimizing Discrete Text Prompts with Reinforcement Learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 3roles
method 1polarities
use method 1representative citing papers
LLMs are highly sensitive to prompt formatting in few-shot settings, with accuracy varying by up to 76 points across formats; FormatSpread samples formats to report performance intervals without model weights.
citing papers explorer
-
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
A hybrid fine-tuning objective using KL divergence for token calibration and Kahneman-Tversky optimization for semantic binding enables LLMs to produce outputs that match desired attribute distributions across repeated prompts.