7 papers
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…
Round-Trip Mutation Testing: Translating Code to Natural Language Intent and back
Asma Hamidi, Cedric Richter, Ahmed Khanfir +1
This paper presents Round-Trip Mutation Testing (RTM), a novel approach that generates mutants from LLM mistranslations between a program code and its intent. Leveraging the genera…
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…
Automatically Evolving Prompt Guidelines for Task-Specific Optimization
Cedric Richter, Salah Ghamizi, Mike Papadakis
For Large Language Models to reliably answer user queries, users must clearly specify requirements, context, and constraints. In practice, however, user queries are often underspec…
Beyond Postconditions: Can Large Language Models infer Formal Contracts for Automatic Software Verification?
Cedric Richter, Heike Wehrheim
Automatic software verifiers have become increasingly effective at the task of checking software against (formal) specifications. Yet, their adoption in practice has been hampered…