LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.
Improving large language model fine-tuning for solving math problems
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Step-DPO performs preference optimization on individual reasoning steps rather than complete answers, producing nearly 3% accuracy gains on MATH for 70B+ parameter models with 10K preference pairs.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
Logic-Regularized Verifier Elicits Reasoning from LLMs
LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.
-
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Step-DPO performs preference optimization on individual reasoning steps rather than complete answers, producing nearly 3% accuracy gains on MATH for 70B+ parameter models with 10K preference pairs.
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.