Saved in:
Bibliographic Details
Main Authors: Wang, Tianduo, Li, Shichen, Lu, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.18248
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916336350789632
author Wang, Tianduo
Li, Shichen
Lu, Wei
author_facet Wang, Tianduo
Li, Shichen
Lu, Wei
contents Effective training of language models (LMs) for mathematical reasoning tasks demands high-quality supervised fine-tuning data. Besides obtaining annotations from human experts, a common alternative is sampling from larger and more powerful LMs. However, this knowledge distillation approach can be costly and unstable, particularly when relying on closed-source, proprietary LMs like GPT-4, whose behaviors are often unpredictable. In this work, we demonstrate that the reasoning abilities of small-scale LMs can be enhanced through self-training, a process where models learn from their own outputs. We also show that the conventional self-training can be further augmented by a preference learning algorithm called Direct Preference Optimization (DPO). By integrating DPO into self-training, we leverage preference data to guide LMs towards more accurate and diverse chain-of-thought reasoning. We evaluate our method across various mathematical reasoning tasks using different base models. Our experiments show that this approach not only improves LMs' reasoning performance but also offers a more cost-effective and scalable solution compared to relying on large proprietary LMs.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18248
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
Wang, Tianduo
Li, Shichen
Lu, Wei
Computation and Language
Effective training of language models (LMs) for mathematical reasoning tasks demands high-quality supervised fine-tuning data. Besides obtaining annotations from human experts, a common alternative is sampling from larger and more powerful LMs. However, this knowledge distillation approach can be costly and unstable, particularly when relying on closed-source, proprietary LMs like GPT-4, whose behaviors are often unpredictable. In this work, we demonstrate that the reasoning abilities of small-scale LMs can be enhanced through self-training, a process where models learn from their own outputs. We also show that the conventional self-training can be further augmented by a preference learning algorithm called Direct Preference Optimization (DPO). By integrating DPO into self-training, we leverage preference data to guide LMs towards more accurate and diverse chain-of-thought reasoning. We evaluate our method across various mathematical reasoning tasks using different base models. Our experiments show that this approach not only improves LMs' reasoning performance but also offers a more cost-effective and scalable solution compared to relying on large proprietary LMs.
title Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
topic Computation and Language
url https://arxiv.org/abs/2407.18248