61 citations · 123 across the 15 of their papers we have counts for
11 papers · 1 filter
From Prompting to Engineering: A Research Agenda for Prompt Engineering in Software Engineering
Vincenzo De Martino, Giovanna Broccia, Fabiano Pecorelli +6
Prompt engineering is increasingly used across Software Engineering (SE) activities, including requirements analysis, coding, testing, documentation, repository analysis, and plann…
Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering
Quim Motger, Alessio Miaschi, Xavier Franch +2
Background. LLM outputs are highly sensitive to prompt formulation: small wording changes can substantially affect output quality. This matters in software engineering, where promp…
Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
Quim Motger, Marc Oriol, Jordi Marco +1
Multi-Agent Debate (MAD) is a promising paradigm for improving the accuracy and robustness of Large Language Model (LLM)-based agentic systems. It enables multiple agents to exchan…
Towards a Software Reference Architecture for Natural Language Processing Tools in Requirements Engineering
Julian Frattini, Quim Motger
Natural Language Processing (NLP) tools support requirements engineering (RE) tasks like requirements elicitation, classification, and validation. However, they are often developed…
FeClustRE: Hierarchical Clustering and Semantic Tagging of App Features from User Reviews
Max Tiessler, Quim Motger
[Context and motivation.] Extracting features from mobile app reviews is increasingly important for multiple requirements engineering (RE) tasks. However, existing methods struggle…
Characterizing Datasets for LLM-based Requirements Engineering: A Systematic Mapping Study
Quim Motger, Carlota Catot, Xavier Franch
Large Language Models (LLMs) depend on high-quality, domain-specific natural language datasets. This dependency is particularly pronounced in Requirements Engineering (RE), where c…
Multi-Agent Debate Strategies to Enhance Requirements Engineering with Large Language Models
Marc Oriol, Quim Motger, Jordi Marco +1
Context: Large Language Model (LLM) agents are becoming widely used for various Requirements Engineering (RE) tasks. Research on improving their accuracy mainly focuses on prompt e…
T-FREX: A Transformer-based Feature Extraction Method from Mobile App Reviews
Quim Motger, Alessio Miaschi, Felice Dell'Orletta +2
Mobile app reviews are a large-scale data source for software-related knowledge generation activities, including software maintenance, evolution and feedback analysis. Effective ex…
Automated Requirements Relation Extraction
Quim Motger, Xavier Franch
In the context of requirements engineering, relation extraction involves identifying and documenting the associations between different requirements artefacts. When dealing with te…
Unveiling Competition Dynamics in Mobile App Markets through User Reviews
Quim Motger, Xavier Franch, Vincenzo Gervasi +1
User reviews published in mobile app repositories are essential for understanding user satisfaction and engagement within a specific market segment. Manual analysis of reviews is i…
Improved management of issue dependencies in issue trackers of large collaborative projects
Mikko Raatikainen, Quim Motger, Clara Marie Lüders +7
Issue trackers, such as Jira, have become the prevalent collaborative tools in software engineering for managing issues, such as requirements, development tasks, and software bugs.…