Indexat a

Llicència i ús

Citacions

Cited 1 times in

Altmetrics

Grant support

This work is supported by the Madrid Government (Comunidad de Madrid - Spain) under the Multiannual Agreement with Universidad Politecnica de Madrid in the line Support for R&D projects for Beatriz Galindo researchers, in the context of the VPRICIT, and through the call Research Grants for Young Investigators from Universidad Politecnica de Madrid. The authors would also like to acknowledge European Union's Horizon Europe Programme under GA 101129744 - EVERSE - HORIZON-INFRA-2023-EOSC-01-02.

Anàlisi d'autories institucional

Compartir

Automated Extraction of Research Software Installation Instructions from README Files: An Initial Analysis

Publicat a:Instant Or Distant: A Temporal Network Tale Of Two Interaction Platforms And Their Influence On Collaboration. 14770 114-133 - 2024-01-01 14770(), DOI: 10.1007/978-3-031-65794-8_8

Autors: Guerrero, CU; Corcho, O; Garijo, D

Afiliacions

Resum

Research Software code projects are typically described with a README files, which often contains the steps to set up, test and run the code contained in them. Installation instructions are written in a human-readable manner and therefore are difficult to interpret by intelligent assistants designed to help other researchers setting up a code repository. In this paper we explore this gap by assessing whether Large Language Models (LLMs) are able to extract installation instruction plans from README files. In particular, we define a methodology to extract alternate installation plans, an evaluation framework to assess the effectiveness of each result and an initial quantitative evaluation based on state of the art LLM models (llama-2-70b-chat and Mixtral-8x7b-Instruct-v0.1). Our results show that while LLMs are a promising approach for finding installation instructions, they present important limitations when these instructions are not sequential or mandatory.

Paraules clau