# Improving the Learning of Code Review Successive Tasks with Cross-Task Knowledge Distillation

arXiv: https://arxiv.org/abs/2402.02063 · HTML: https://mlsanity.com/paper/2402.02063/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2024.

## Built on by (most cited first, 7 of 7)

- [CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences](https://mlsanity.com/paper/2403.09032/) (2024)
- [Combining Large Language Models with Static Analyzers for Code Review Generation](https://mlsanity.com/paper/2502.06633/) (2025)
- [Leveraging Reviewer Experience in Code Review Comment Generation](https://mlsanity.com/paper/2409.10959/) (2024)
- [Issue-Oriented Agent-Based Framework for Automated Review Comment Generation](https://mlsanity.com/paper/2511.00517/) (2025)
- [Towards Practical Defect-Focused Automated Code Review](https://mlsanity.com/paper/2505.17928/) (2025)
- [Leveraging Reward Models for Guiding Code Review Comment Generation](https://mlsanity.com/paper/2506.04464/) (2025)
- [Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation](https://mlsanity.com/paper/2604.15270/) (2026)

## Abstract (arXiv)

Code review is a fundamental process in software development that plays a pivotal role in ensuring code quality and reducing the likelihood of errors and bugs. However, code review can be complex, subjective, and time-consuming. Quality estimation, comment generation, and code refinement constitute the three key tasks of this process, and their automation has traditionally been addressed separately in the literature using different approaches. In particular, recent efforts have focused on fine-tuning pre-trained language models to aid in code review tasks, with each task being considered in isolation. We believe that these tasks are interconnected, and their fine-tuning should consider this interconnection. In this paper, we introduce a novel deep-learning architecture, named DISCOREV, which employs cross-task knowledge distillation to address these tasks simultaneously. In our approach, we utilize a cascade of models to enhance both comment generation and code refinement models. The fine-tuning of the comment generation model is guided by the code refinement model, while the fine-tuning of the code refinement model is guided by the quality estimation model. We implement this guidance using two strategies: a feedback-based learning objective and an embedding alignment objective. We evaluate DISCOREV by comparing it to state-of-the-art methods based on independent training and fine-tuning. Our results show that our approach generates better review comments, as measured by the BLEU score, as well as more accurate code refinement according to the CodeBLEU score