Tricky$^2$: Towards a Benchmark for Evaluating Human and LLM Error Interactions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Granger, Cole, Khati, Dipin, Rodriguez-Cardenas, Daniel, Poshyvanyk, Denys
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911401639936000
author Granger, Cole
Khati, Dipin
Rodriguez-Cardenas, Daniel
Poshyvanyk, Denys
author_facet Granger, Cole
Khati, Dipin
Rodriguez-Cardenas, Daniel
Poshyvanyk, Denys
contents Large language models (LLMs) are increasingly integrated into software development workflows, yet they often introduce subtle logic or data-misuse errors that differ from human bugs. To study how these two error types interact, we construct Tricky$^2$, a hybrid dataset that augments the existing TrickyBugs corpus of human-written defects with errors injected by both GPT-5 and OpenAI-oss-20b across C++, Python, and Java programs. Our approach uses a taxonomy-guided prompting framework to generate machine-originated bugs while preserving original human defects and program structure. The resulting corpus spans human-only, LLM-only, and human+LLM splits, enabling analysis of mixed-origin error behavior, multi-bug repair robustness, and reliability in hybrid human-machine code. This paper outlines the dataset construction pipeline and illustrates its use through small-scale baseline evaluations of classification, localization, and repair tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18949
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tricky$^2$: Towards a Benchmark for Evaluating Human and LLM Error Interactions
Granger, Cole
Khati, Dipin
Rodriguez-Cardenas, Daniel
Poshyvanyk, Denys
Software Engineering
Artificial Intelligence
Large language models (LLMs) are increasingly integrated into software development workflows, yet they often introduce subtle logic or data-misuse errors that differ from human bugs. To study how these two error types interact, we construct Tricky$^2$, a hybrid dataset that augments the existing TrickyBugs corpus of human-written defects with errors injected by both GPT-5 and OpenAI-oss-20b across C++, Python, and Java programs. Our approach uses a taxonomy-guided prompting framework to generate machine-originated bugs while preserving original human defects and program structure. The resulting corpus spans human-only, LLM-only, and human+LLM splits, enabling analysis of mixed-origin error behavior, multi-bug repair robustness, and reliability in hybrid human-machine code. This paper outlines the dataset construction pipeline and illustrates its use through small-scale baseline evaluations of classification, localization, and repair tasks.
title Tricky$^2$: Towards a Benchmark for Evaluating Human and LLM Error Interactions
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2601.18949