Papers › TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer

TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer

18 Jul 2021ICML 2021 7archive 2025-07-28

Berkay Berabi, Jingxuan He, Veselin Raychev, Martin Vechev

The problem of fixing errors in programs has attracted substantial interest over the years. The key challenge for building an effective code fixing tool is to capture a wide range of errors and meanwhile maintain high accuracy. In this paper, we address this challenge and present a new learning-based system, called TFix. TFix works directly on program text and phrases the problem of code fixing as a text-to-text task. In turn, this enables it to leverage a powerful Transformer based model pre-trained on natural language and fine-tuned to generate code fixes (via a large, high-quality dataset obtained from GitHub commits). TFix is not specific to a particular programming language or class of defects and, in fact, improved its precision by simultaneously fine-tuning on 52 different error types reported by a popular static analyzer. Our evaluation on a massive dataset of JavaScript programs shows that TFix is practically effective: it is able to synthesize code that fixes the error in 67 percent of cases and significantly outperforms existing learning-based approaches.

Paper PDF Code

Code

eth-sri/TFix mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Code Generation Multi-Task Learning Program Repair Transfer Learning

Datasets

Introduced by this paper, per the archive.

TFix's Code Patches Data

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Program Repair	TFix's Code Patches Data	TFix	Error Removal	67,8	#1 of 1	Archive leaderboard	report
Program Repair	TFix's Code Patches Data	TFix	Exact Match	49,3	#1 of 1	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections