Reasoning through Perspective Transition (RPT) improves LLM performance on subjective NLP tasks by ranking direct, role, and third-person perspectives by self-reported confidence and answering from the top-ranked perspective.
Improved Training for Self-Training by Confidence Assessments
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
It is well known that for some tasks, labeled data sets may be hard to gather. Therefore, we wished to tackle here the problem of having insufficient training data. We examined learning methods from unlabeled data after an initial training on a limited labeled data set. The suggested approach can be used as an online learning method on the unlabeled test set. In the general classification task, whenever we predict a label with high enough confidence, we treat it as a true label and train the data accordingly. For the semantic segmentation task, a classic example for an expensive data labeling process, we do so pixel-wise. Our suggested approaches were applied on the MNIST data-set as a proof of concept for a vision classification task and on the ADE20K data-set in order to tackle the semi-supervised semantic segmentation problem.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Perspective Transition of Large Language Models for Solving Subjective Tasks
Reasoning through Perspective Transition (RPT) improves LLM performance on subjective NLP tasks by ranking direct, role, and third-person perspectives by self-reported confidence and answering from the top-ranked perspective.