# Not the Silver Bullet: LLM-enhanced Programming Error Messages are Ineffective in Practice

arXiv: https://arxiv.org/abs/2409.18661 · HTML: https://mlsanity.com/paper/2409.18661/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 52 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Builds on (most cited first, 9 of 9)

- [Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation](https://mlsanity.com/paper/2212.01020/) (2022)
- [Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming](https://mlsanity.com/paper/2210.14306/) (2022)
- [Using Large Language Models to Enhance Programming Error Messages](https://mlsanity.com/paper/2210.11630/) (2022)
- ["It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmers](https://mlsanity.com/paper/2304.02491/) (2023)
- [Prompt Problems: A New Programming Exercise for the Generative AI Era](https://mlsanity.com/paper/2311.05943/) (2023)
- [How Beginning Programmers and Code LLMs (Mis)read Each Other](https://mlsanity.com/paper/2401.15232/) (2024)
- [The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers](https://mlsanity.com/paper/2404.02806/) (2024)
- [Ironies of Generative AI: Understanding and mitigating productivity loss in human-AI interactions](https://mlsanity.com/paper/2402.11364/) (2024)
- ["ChatGPT Is Here to Help, Not to Replace Anybody" -- An Evaluation of Students' Opinions On Integrating ChatGPT In CS Courses](https://mlsanity.com/paper/2404.17443/) (2024)

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

- [Breaking the Programming Language Barrier: Multilingual Prompting to Empower Non-Native English Learners](https://mlsanity.com/paper/2412.12800/) (2024)
- [Narrowing the Gap: Supervised Fine-Tuning of Open-Source LLMs as a Viable Alternative to Proprietary Models for Pedagogical Tools](https://mlsanity.com/paper/2507.05305/) (2025)

## Abstract (arXiv)

The sudden emergence of large language models (LLMs) such as ChatGPT has had a disruptive impact throughout the computing education community. LLMs have been shown to excel at producing correct code to CS1 and CS2 problems, and can even act as friendly assistants to students learning how to code. Recent work shows that LLMs demonstrate unequivocally superior results in being able to explain and resolve compiler error messages -- for decades, one of the most frustrating parts of learning how to code. However, LLM-generated error message explanations have only been assessed by expert programmers in artificial conditions. This work sought to understand how novice programmers resolve programming error messages (PEMs) in a more realistic scenario. We ran a within-subjects study with n = 106 participants in which students were tasked to fix six buggy C programs. For each program, participants were randomly assigned to fix the problem using either a stock compiler error message, an expert-handwritten error message, or an error message explanation generated by GPT-4. Despite promising evidence on synthetic benchmarks, we found that GPT-4 generated error messages outperformed conventional compiler error messages in only 1 of the 6 tasks, measured by students' time-to-fix each problem. Handwritten explanations still outperform LLM and conventional error messages, both on objective and subjective measures.