# Learning to Blame: Localizing Novice Type Errors with Data-Driven Diagnosis

arXiv: https://arxiv.org/abs/1708.07583 · HTML: https://mlsanity.com/paper/1708.07583/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2017.

## Built on by (most cited first, 2 of 2)

- [Novice Type Error Diagnosis with Natural Language Models](https://mlsanity.com/paper/2210.03682/) (2022)
- [Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code](https://mlsanity.com/paper/2607.13921/) (2026)

## Abstract (arXiv)

Localizing type errors is challenging in languages with global type inference, as the type checker must make assumptions about what the programmer intended to do. We introduce Nate, a data-driven approach to error localization based on supervised learning. Nate analyzes a large corpus of training data -- pairs of ill-typed programs and their "fixed" versions -- to automatically learn a model of where the error is most likely to be found. Given a new ill-typed program, Nate executes the model to generate a list of potential blame assignments ranked by likelihood. We evaluate Nate by comparing its precision to the state of the art on a set of over 5,000 ill-typed OCaml programs drawn from two instances of an introductory programming course. We show that when the top-ranked blame assignment is considered, Nate's data-driven model is able to correctly predict the exact sub-expression that should be changed 72% of the time, 28 points higher than OCaml and 16 points higher than the state-of-the-art SHErrLoc tool. Furthermore, Nate's accuracy surpasses 85% when we consider the top two locations and reaches 91% if we consider the top three.