Saved in:
Bibliographic Details
Main Authors: Baltes, Sebastian, Angermeir, Florian, Arora, Chetan, Barón, Marvin Muñoz, Chen, Chunyang, Böhme, Lukas, Calefato, Fabio, Ernst, Neil, Falessi, Davide, Fitzgerald, Brian, Fucci, Davide, He, Junda, Treude, Christoph, Kalinowski, Marcos, Lambiase, Stefano, Russo, Daniel, Lungu, Mircea, Montes, Cristina Martinez, Prechelt, Lutz, Ralph, Paul, van Tonder, Rijnard, Wagner, Stefan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.15503
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910247023542272
author Baltes, Sebastian
Angermeir, Florian
Arora, Chetan
Barón, Marvin Muñoz
Chen, Chunyang
Böhme, Lukas
Calefato, Fabio
Ernst, Neil
Falessi, Davide
Fitzgerald, Brian
Fucci, Davide
He, Junda
Treude, Christoph
Kalinowski, Marcos
Lambiase, Stefano
Russo, Daniel
Lungu, Mircea
Montes, Cristina Martinez
Prechelt, Lutz
Ralph, Paul
van Tonder, Rijnard
Wagner, Stefan
author_facet Baltes, Sebastian
Angermeir, Florian
Arora, Chetan
Barón, Marvin Muñoz
Chen, Chunyang
Böhme, Lukas
Calefato, Fabio
Ernst, Neil
Falessi, Davide
Fitzgerald, Brian
Fucci, Davide
He, Junda
Treude, Christoph
Kalinowski, Marcos
Lambiase, Stefano
Russo, Daniel
Lungu, Mircea
Montes, Cristina Martinez
Prechelt, Lutz
Ralph, Paul
van Tonder, Rijnard
Wagner, Stefan
contents Large Language Models (LLMs) are widely used in software engineering (SE) research and practice, yet their non-determinism, opaque training data, and rapidly evolving models threaten the reproducibility and replicability of empirical studies. We address this challenge through a collaborative effort of 22 researchers, presenting a taxonomy of seven study types that organizes how LLMs are used in SE research, together with eight guidelines for designing and reporting such studies. Each guideline distinguishes requirements (must) from recommended practices (should) and is contextualized by the study types it applies to. Our guidelines recommend that researchers: (1) declare LLM usage and role; (2) report model versions, configurations, and customizations; (3) document the tool architecture beyond the model; (4) disclose prompts, their development, and interaction logs; (5) validate LLM outputs with humans; (6) include an open LLM as a baseline; (7) use suitable baselines, benchmarks, and metrics; and (8) articulate limitations and mitigations. We complement the guidelines with an applicability matrix mapping guidelines to study types and a reporting checklist for authors and reviewers. We maintain the study types and guidelines online as a living resource for the community to use and shape (llm-guidelines$.$org).
format Preprint
id arxiv_https___arxiv_org_abs_2508_15503
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Guidelines for Empirical Studies in Software Engineering involving Large Language Models
Baltes, Sebastian
Angermeir, Florian
Arora, Chetan
Barón, Marvin Muñoz
Chen, Chunyang
Böhme, Lukas
Calefato, Fabio
Ernst, Neil
Falessi, Davide
Fitzgerald, Brian
Fucci, Davide
He, Junda
Treude, Christoph
Kalinowski, Marcos
Lambiase, Stefano
Russo, Daniel
Lungu, Mircea
Montes, Cristina Martinez
Prechelt, Lutz
Ralph, Paul
van Tonder, Rijnard
Wagner, Stefan
Software Engineering
Large Language Models (LLMs) are widely used in software engineering (SE) research and practice, yet their non-determinism, opaque training data, and rapidly evolving models threaten the reproducibility and replicability of empirical studies. We address this challenge through a collaborative effort of 22 researchers, presenting a taxonomy of seven study types that organizes how LLMs are used in SE research, together with eight guidelines for designing and reporting such studies. Each guideline distinguishes requirements (must) from recommended practices (should) and is contextualized by the study types it applies to. Our guidelines recommend that researchers: (1) declare LLM usage and role; (2) report model versions, configurations, and customizations; (3) document the tool architecture beyond the model; (4) disclose prompts, their development, and interaction logs; (5) validate LLM outputs with humans; (6) include an open LLM as a baseline; (7) use suitable baselines, benchmarks, and metrics; and (8) articulate limitations and mitigations. We complement the guidelines with an applicability matrix mapping guidelines to study types and a reporting checklist for authors and reviewers. We maintain the study types and guidelines online as a living resource for the community to use and shape (llm-guidelines$.$org).
title Guidelines for Empirical Studies in Software Engineering involving Large Language Models
topic Software Engineering
url https://arxiv.org/abs/2508.15503