Papers
arxiv:2511.01043

DPO-F+: Aligning Code Repair Feedback with Developers' Preferences

Published on Nov 2, 2025
Authors:
,
,
,
,

Abstract

DPO-f+ enhances code repair by aligning LLM feedback with developer needs through profiled metrics, preference dataset construction, and fine-tuning with Direct Preference Optimization.

Large Language Models (LLMs) are increasingly applied to software engineering tasks, especially code repair. However, developers often struggle to interpret model outputs, limiting effective human-AI teaming. Prior work largely optimizes repaired code while under-addressing the natural-language feedback that enables comprehension and iterative improvement. We present DPO-f+, a novel framework that aligns code-repair feedback with developer needs and profiles. It (1) formalizes developer-profiled, domain-specific metrics for feedback alignment; (2) automatically constructs pairwise preference datasets from code-repair tasks; (3) fine-tunes using Direct Preference Optimization (DPO) augmented with a lightweight margin signal; and (4) provides an automated feedback evaluation protocol. Empirically, DPO-f+ outperforms both the baseline and standard DPO on generated-code accuracy and overall feedback alignment. On novice programming tasks, DPO-f+ raises the top-1 pass rate by 5.71 percentage points (pp) over the baseline and by 3.30 pp over DPO. On the more challenging SWE-bench Lite benchmark, it increases the issue-resolution rate by 1.67 pp over DPO and by 4.67 pp over the baseline. It also achieves the largest improvement in feedback alignment, outperforming DPO and the baseline. By aligning feedback more closely with developer needs, DPO-f+ turns LLM-assisted repair from one-shot outputs into a collaborative sensemaking workflow, providing a practical approach to enhancing code comprehension and fostering more effective human-AI teaming in software engineering.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2511.01043
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2511.01043 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2511.01043 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2511.01043 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.