Context Generation for Code and Architecture Changes Using Large Language Models: Unterschied zwischen den Versionen
(Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Ian Winter |email=uekip@student.kit.edu |vortragstyp=Masterarbeit |betreuer=Yves Kirschner |termin=Institutsseminar/2024-03-08 |vortragsmodus=in Präsenz |kurzfassung=TBD }}“) |
Keine Bearbeitungszusammenfassung |
||
Zeile 6: | Zeile 6: | ||
|termin=Institutsseminar/2024-03-08 | |termin=Institutsseminar/2024-03-08 | ||
|vortragsmodus=in Präsenz | |vortragsmodus=in Präsenz | ||
|kurzfassung= | |kurzfassung=While large language models have succeeded in generating code, the struggle is to modify large existing code bases. The Generated Code Alteration (GCA) process is designed, implemented, and evaluated in this thesis. The GCA process can automatically modify a large existing code base, given a natural language task. Different variations and instantiations of the process are evaluated in an industrial case study. The code generated by the GCA process is compared to code written by human developers. The language model-based GCA process was able to generate 13.3 lines per error, while the human baseline generated 65.8 lines per error. While the generated code did not match the overall human performance in modifying large code bases, it could still provide assistance to human developers. | ||
}} | }} |
Aktuelle Version vom 26. Februar 2024, 11:11 Uhr
Vortragende(r) | Ian Winter | |
---|---|---|
Vortragstyp | Masterarbeit | |
Betreuer(in) | Yves Kirschner | |
Termin | Fr 8. März 2024 | |
Vortragsmodus | in Präsenz | |
Kurzfassung | While large language models have succeeded in generating code, the struggle is to modify large existing code bases. The Generated Code Alteration (GCA) process is designed, implemented, and evaluated in this thesis. The GCA process can automatically modify a large existing code base, given a natural language task. Different variations and instantiations of the process are evaluated in an industrial case study. The code generated by the GCA process is compared to code written by human developers. The language model-based GCA process was able to generate 13.3 lines per error, while the human baseline generated 65.8 lines per error. While the generated code did not match the overall human performance in modifying large code bases, it could still provide assistance to human developers. |