Same Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled Code

• URL: http://arxiv.org/abs/2606.26505v1
• Date: Thu, 25 Jun 2026 01:23:05 GMT
• Title: Same Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled Code
• Abstract summary: We conduct a Wizard-of-Oz experiment to examine how software engineers behave when code is explicitly labeled as LLM-generated during a code review task.<n>We found that while the thoroughness of code review did not change for participants, they spent more time fixating on LLM-labelled code, indicating that the label itself influences attention.<n> Practitioners also adapted their review strategy for LLM-labelled code by assessing the code based on specific criteria, or using the prompt to guide their review.
• Score: 3.7910079742785787
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern software development increasingly involves the use of large language models (LLMs) to generate code. Despite their rapid advancement, LLMs remain prone to errors and hallucinations, emphasizing the importance of careful code inspection. However, in practice, developers' trust in LLM-generated code and their willingness to review it thoroughly may differ from these recommendations. How developers actually behave when reviewing LLM-generated code remains largely unexplored. In this study, we conduct a Wizard-of-Oz experiment to examine how software engineers behave when code is explicitly labeled as LLM-generated during a code review task. We collect both behavioral data and participant feedback through eye-tracking and exit interviews. Combining Bayesian data analysis with qualitative analysis, we found that while the thoroughness of code review did not change for participants, they spent more time fixating on LLM-labelled code, indicating that the label itself influences attention. Practitioners also adapted their review strategy for LLM-labelled code by assessing the code based on specific criteria (e.g., logical correctness), or using the prompt to guide their review. These findings inform LLM-based tool design on labelling while incorporating the prompt as a software artifact. Our study reveals a gap between reviewers' intentions and actual reviewing behaviour, highlighting the need for software companies to revisit their AI policies (particularly regarding LLM-assisted development) to better support developers in reviewing LLM-generated code.

Related papers

• An Exploratory Study on LLM-Generated Code and Comments in Code Repositories [6.161007996548193]
  We study the code and comments detected as likely to be generated by LLMs and their characteristics.<n>We conduct experiments on active company- and community-maintained repositories from 2021 to 2025.
  arXiv  Detail & Related papers  (2026-07-02T08:25:15Z)
• Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement [8.059802912761919]
  We uncover a systematic failure of large language models (LLMs) in matching code to natural language requirements.<n>More detailed prompt design, particularly with those requiring explanations and proposed corrections, leads to higher misjudgment rates.<n>We propose a Fix-guided Verification Filter that treats the model proposed fix as executable counterfactual evidence.
  arXiv  Detail & Related papers  (2026-02-28T08:35:25Z)
• CodeSimpleQA: Scaling Factuality in Code Large Language Models [55.705748501461294]
  We present CodeSimpleQA, a comprehensive benchmark designed to evaluate the factual accuracy of code LLMs in answering code-related questions.<n>We also create CodeSimpleQA-Instruct, a large-scale instruction corpus with 66M samples, and develop a post-training framework combining supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-12-22T14:27:17Z)
• Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications [0.6813925418351435]
  Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks.<n>In this paper, we uncover a systematic failure of LLMs in evaluating whether code aligns with natural language requirements.<n>Our results reveal that LLMs frequently misclassify correct code implementations as either not satisfying requirements'' or containing potential defects.
  arXiv  Detail & Related papers  (2025-08-17T13:07:26Z)
• How Accurately Do Large Language Models Understand Code? [4.817546726074033]
  Large Language Models (LLMs) are increasingly used in post-development tasks such as code repair and testing.<n> Quantifying code comprehension is challenging due to its abstract nature and the lack of a standardized metric.<n>This paper presents the first large-scale empirical investigation into LLMs' ability to understand code.
  arXiv  Detail & Related papers  (2025-04-06T05:59:29Z)
• What's Wrong with Your Code Generated by Large Language Models? An Extensive Study [92.62952504133926]
  This study evaluated the performance of three leading closed-source LLMs and six popular open-source LLMs on three commonly used benchmarks.<n>We developed a taxonomy of bugs for incorrect codes and analyzed the root cause for common bug types.<n>We propose a novel training-free iterative method that introduces self-critique, enabling LLMs to critique and correct their generated code.
  arXiv  Detail & Related papers  (2024-07-08T17:27:17Z)
• A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions [13.58143103712]
  GitHub Copilot is a large language model (LLM)-powered code generation tool. This paper investigates how developers validate and repair code generated by Copilot. Being aware of the code's provenance led to improved performance, increased search efforts, more frequent Copilot usage, and higher cognitive workload.
  arXiv  Detail & Related papers  (2024-05-25T06:20:01Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models [56.723509505549536]
  InfiBench is the first large-scale freeform question-answering (QA) benchmark for code to our knowledge. It comprises 234 carefully selected high-quality Stack Overflow questions that span across 15 programming languages. We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings.
  arXiv  Detail & Related papers  (2024-03-11T02:06:30Z)
• Assured LLM-Based Software Engineering [51.003878077888686]
  This paper is an outline of the content of the keynote by Mark Harman at the International Workshop on Interpretability, Robustness, and Benchmarking in Neural Software Engineering, Monday 15th April 2024, Lisbon, Portugal.
  arXiv  Detail & Related papers  (2024-02-06T20:38:46Z)
• Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs [65.2379940117181]
  We introduce code prompting, a chain of prompts that transforms a natural language problem into code. We find that code prompting exhibits a high-performance boost for multiple LLMs. Our analysis of GPT 3.5 reveals that the code formatting of the input problem is essential for performance improvement.
  arXiv  Detail & Related papers  (2024-01-18T15:32:24Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.