A generative preference-learning method trains a latent demonstration selector from LLM feedback and improves few-shot in-context learning performance on most of 19 benchmark datasets.
Boosting Deductive Reasoning with Step Signals In RLHF
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Logical reasoning is a crucial task for Large Language Models (LLMs), enabling them to tackle complex problems. Among reasoning tasks, multi-step reasoning poses a particular challenge. Grounded in the theory of formal logic, we have developed an automated method, Multi-step Deduction (MuseD), for deductive reasoning data. MuseD has allowed us to create training and testing datasets for multi-step reasoning. Our generation method enables control over the complexity of the generated instructions, facilitating training and evaluation of models across different difficulty levels. Through RLHF training, our training data has demonstrated significant improvements in logical capabilities for both in-domain of out-of-domain reasoning tasks. Additionally, we have conducted tests to assess the multi-step reasoning abilities of various models.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Select In-Context Demonstration Preferred by Large Language Model
A generative preference-learning method trains a latent demonstration selector from LLM feedback and improves few-shot in-context learning performance on most of 19 benchmark datasets.