Maninger, Daniel ; Narasimhan, Krishna ; Mezini, Mira (2024)
Towards Trustworthy AI Software Development Assistance.
44th International Conference on Software Engineering: New Ideas and Emerging Results. Lisbon, Portugal (14.04.2024 - 20.04.2024)
doi: 10.1145/3639476.3639770
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
It is expected that in the near future, AI software development assistants will play an important role in the software industry. However, current software development assistants tend to be unreliable, often producing incorrect, unsafe, or low-quality code. We seek to resolve these issues by introducing a holistic architecture for constructing, training, and using trustworthy AI software development assistants. In the center of the architecture, there is a foundational LLM trained on datasets representative of real-world coding scenarios and complex software architectures, and fine-tuned on code quality criteria beyond correctness. The LLM will make use of graph-based code representations for advanced semantic comprehension. We envision a knowledge graph integrated into the system to provide up-to-date background knowledge and to enable the assistant to provide appropriate explanations. Finally, a modular framework for constrained decoding will ensure that certain guarantees (e.g., for correctness and security) hold for the generated code.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Maninger, Daniel ; Narasimhan, Krishna ; Mezini, Mira |
| Art des Eintrags: | Bibliographie |
| Titel: | Towards Trustworthy AI Software Development Assistance |
| Sprache: | Englisch |
| Publikationsjahr: | 24 Mai 2024 |
| Verlag: | ACM |
| Buchtitel: | ICSE-NIER'24 : Proceedings of the 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results |
| Reihe: | ICSE-NIER'24 |
| Veranstaltungstitel: | 44th International Conference on Software Engineering: New Ideas and Emerging Results |
| Veranstaltungsort: | Lisbon, Portugal |
| Veranstaltungsdatum: | 14.04.2024 - 20.04.2024 |
| DOI: | 10.1145/3639476.3639770 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | It is expected that in the near future, AI software development assistants will play an important role in the software industry. However, current software development assistants tend to be unreliable, often producing incorrect, unsafe, or low-quality code. We seek to resolve these issues by introducing a holistic architecture for constructing, training, and using trustworthy AI software development assistants. In the center of the architecture, there is a foundational LLM trained on datasets representative of real-world coding scenarios and complex software architectures, and fine-tuned on code quality criteria beyond correctness. The LLM will make use of graph-based code representations for advanced semantic comprehension. We envision a knowledge graph integrated into the system to provide up-to-date background knowledge and to enable the assistant to provide appropriate explanations. Finally, a modular framework for constrained decoding will ensure that certain guarantees (e.g., for correctness and security) hold for the generated code. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Softwaretechnik |
| Hinterlegungsdatum: | 03 Jun 2024 11:52 |
| Letzte Änderung: | 09 Okt 2024 13:14 |
| PPN: | 522052665 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum