# KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair

arXiv: https://arxiv.org/abs/2302.01857 · HTML: https://mlsanity.com/paper/2302.01857/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 66 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018)
- [Harnessing Deep Neural Networks with Logic Rules](https://mlsanity.com/paper/1603.06318/) (2016)
- [An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation](https://mlsanity.com/paper/1812.08693/) (2018)
- [Abstract Syntax Networks for Code Generation and Semantic Parsing](https://mlsanity.com/paper/1704.07535/) (2017)
- [TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation](https://mlsanity.com/paper/1810.02720/) (2018)
- [CURE: Code-Aware Neural Machine Translation for Automatic Program Repair](https://mlsanity.com/paper/2103.00073/) (2021)
- [Latent Predictor Networks for Code Generation](https://mlsanity.com/paper/1603.06744/) (2016)
- [TBar: Revisiting Template-based Automated Program Repair](https://mlsanity.com/paper/1903.08409/) (2019)
- [TreeGen: A Tree-Based Transformer Architecture for Code Generation](https://mlsanity.com/paper/1911.09983/) (2019)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [On Learning Meaningful Code Changes via Neural Machine Translation](https://mlsanity.com/paper/1901.09102/) (2019)
- [Neural Program Repair with Execution-based Backpropagation](https://mlsanity.com/paper/2105.04123/) (2021)
- [CODIT: Code Editing with Tree-Based Neural Models](https://mlsanity.com/paper/1810.00314/) (2018)
- [Neural Transfer Learning for Repairing Security Vulnerabilities in C Code](https://mlsanity.com/paper/2104.08308/) (2021)
- [Learning to Represent Edits](https://mlsanity.com/paper/1810.13337/) (2018)
- [SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics](https://mlsanity.com/paper/2203.12755/) (2022)
- [Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs](https://mlsanity.com/paper/1811.04211/) (2018)
- [ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programming](https://mlsanity.com/paper/1712.07804/) (2017)

## Built on by (most cited first, 13 of 13)

- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [How Effective Are Neural Networks for Fixing Security Vulnerabilities](https://mlsanity.com/paper/2305.18607/) (2023)
- [Rectifier: Code Translation with Corrector via LLMs](https://mlsanity.com/paper/2407.07472/) (2024)
- [ITER: Iterative Neural Repair for Multi-Location Patches](https://mlsanity.com/paper/2304.12015/) (2023)
- [Extending the Frontier of ChatGPT: Code Generation and Debugging](https://mlsanity.com/paper/2307.08260/) (2023)
- [Can Agents Fix Agent Issues?](https://mlsanity.com/paper/2505.20749/) (2025)
- [Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2310.10698/) (2023)
- [Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends](https://mlsanity.com/paper/2401.07518/) (2024)
- [Evaluating the Generalizability of LLMs in Automated Program Repair](https://mlsanity.com/paper/2503.09217/) (2025)
- [Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation](https://mlsanity.com/paper/2506.22776/) (2025)
- [Redundancy and Concept Analysis for Code-trained Language Models](https://mlsanity.com/paper/2305.00875/) (2023)
- [BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models](https://mlsanity.com/paper/2605.09134/) (2026)
- [CaBaGe: Data-Free Model Extraction using ClAss BAlanced Generator Ensemble](https://mlsanity.com/paper/2409.10643/) (2024)

## Abstract (arXiv)

Automated Program Repair (APR) improves software reliability by generating patches for a buggy program automatically. Recent APR techniques leverage deep learning (DL) to build models to learn to generate patches from existing patches and code corpora. While promising, DL-based APR techniques suffer from the abundant syntactically or semantically incorrect patches in the patch space. These patches often disobey the syntactic and semantic domain knowledge of source code and thus cannot be the correct patches to fix a bug. We propose a DL-based APR approach KNOD, which incorporates domain knowledge to guide patch generation in a direct and comprehensive way. KNOD has two major novelties, including (1) a novel three-stage tree decoder, which directly generates Abstract Syntax Trees of patched code according to the inherent tree structure, and (2) a novel domain-rule distillation, which leverages syntactic and semantic rules and teacher-student distributions to explicitly inject the domain knowledge into the decoding procedure during both the training and inference phases. We evaluate KNOD on three widely-used benchmarks. KNOD fixes 72 bugs on the Defects4J v1.2, 25 bugs on the QuixBugs, and 50 bugs on the additional Defects4J v2.0 benchmarks, outperforming all existing APR tools.