Saved in:
Bibliographic Details
Main Authors: Feng, Yuming, Yang, Christy
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.20100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914411607752704
author Feng, Yuming
Yang, Christy
author_facet Feng, Yuming
Yang, Christy
contents Direct Preference Optimization (DPO) is widely used after supervised fine-tuning (SFT) to align language models, yet empirical behavior under small backbones and modest data is under-specified. We systematically compare SFT-only, DPO-only, and staged SFT-to-DPO training alongside full fine-tuning (FFT) versus LoRA on a GPT-2-scale decoder, evaluating paraphrase detection and Shakespearean sonnet continuation. DPO yields small, task-dependent gains over strong SFT and can match competitive SFT accuracy without a warm start when the preference construction closely parallels the supervised objective. In contrast, parameterization dominates: FFT consistently outperforms LoRA at matched training depth, and LoRA does not reduce wall-clock time on our hardware. These findings indicate that, in this small-scale regime, supervised full-parameter adaptation remains the primary performance lever, while preference optimization and low-rank adaptation provide limited marginal returns.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20100
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models
Feng, Yuming
Yang, Christy
Computation and Language
Artificial Intelligence
Direct Preference Optimization (DPO) is widely used after supervised fine-tuning (SFT) to align language models, yet empirical behavior under small backbones and modest data is under-specified. We systematically compare SFT-only, DPO-only, and staged SFT-to-DPO training alongside full fine-tuning (FFT) versus LoRA on a GPT-2-scale decoder, evaluating paraphrase detection and Shakespearean sonnet continuation. DPO yields small, task-dependent gains over strong SFT and can match competitive SFT accuracy without a warm start when the preference construction closely parallels the supervised objective. In contrast, parameterization dominates: FFT consistently outperforms LoRA at matched training depth, and LoRA does not reduce wall-clock time on our hardware. These findings indicate that, in this small-scale regime, supervised full-parameter adaptation remains the primary performance lever, while preference optimization and low-rank adaptation provide limited marginal returns.
title An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.20100