Breaking the Silence: the Threats of Using LLMs in Software Engineering

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

416 Downloads (Pure)


Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization. Despite their promise, researchers must still be careful as numerous intricate factors can influence the outcomes of experiments involving LLMs.
This paper initiates an open discussion on potential threats to the validity of LLM-based research including issues such as closed-source models, possible data leakage between LLM training data and research evaluation, and the reproducibility of LLM-based findings.
In response, this paper proposes a set of guidelines tailored for SE researchers and Language Model (LM) providers to mitigate these concerns.
The implications of the guidelines are illustrated using existing good practices followed by LLM providers and a practical example for SE researchers in the context of test case generation.
Original languageEnglish
Title of host publicationACM/IEEE 46th International Conference on Software Engineering - New Ideas and Emerging Results
Number of pages5
ISBN (Electronic)979-8-4007-0500-7/24/04
Publication statusAccepted/In press - Jan 2024
EventACM/IEEE 46th International Conference on Software Engineering - Lisbon, Lisbon, Portugal
Duration: 14 Apr 202420 Apr 2024
Conference number: 46


ConferenceACM/IEEE 46th International Conference on Software Engineering
Abbreviated title ICSE '24
Internet address


  • Large Language Models
  • Artificial Intelligence
  • Empirical Software Engineering
  • Empirical Software Validation


Dive into the research topics of 'Breaking the Silence: the Threats of Using LLMs in Software Engineering'. Together they form a unique fingerprint.

Cite this