From the 1 of 15 linked papers with an AI index.
15 papers
SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests
Maha Ayub, Michael Konstantinou, Ahmed Khanfir +2
The paper introduces SemaDiff, a method that uses large language models to generate additional calling code and tests in order to compare the behavior of pre- and post‑commit versi…
On the risk of coding before testing: An empirical study on LLM-based test generation workflow
Michael Konstantinou, Florian Tambon, Mike Papadakis
Large Language Models (LLMs) are increasingly used in software engineering workflows to generate both source code and test suites. This dual capability has enabled emerging develop…
From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation
Amal Akli, Melissa Akli, Cedric Richter +2
Large language models are known to be sensitive to prompt formulation. Even minor variations in wording can substantially degrade performance. This sensitivity reveals an opportuni…
Prompt Coverage Adequacy
Florian Tambon, Michael Konstantinou, Cedric Richter +3
In recent years, it has become increasingly evident that large language models (LLMs) and autonomous agents raise the level of abstraction in software development by shifting the f…
Underspecification does not imply Incoherence: The Risks of Semantic Collapse in Coding Models
Cedric Richter, Mike Papadakis
Large Language Models (LLMs) have become increasingly effective at generating code when task descriptions are clear and precise. Yet, in practice, user-provided task descriptions a…
Inferring Code Correctness from Specification
Tambon Florian, Papadakis Mike
Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the correctness of LLM-generated…