Comparing Large Language Models and Grammatical Evolution for Code Generation
Created by W.Langdon from
gp-bibliography.bib Revision:1.7954
- @InProceedings{custode:2024:GECCOcomp,
-
author = "Leonardo Lucio Custode and
Chiara Camilla {Migliore Rambaldi} and Marco Roveri and Giovanni Iacca",
-
title = "Comparing Large Language Models and Grammatical
Evolution for Code Generation",
-
booktitle = "Large Language Models for and with Evolutionary
Computation Workshop",
-
year = "2024",
-
editor = "Erik Hemberg and Roman Senkerik and
Una-May O'Reilly and Michal Pluhacek and Tome Eftimov",
-
pages = "1830--1837",
-
address = "Melbourne, Australia",
-
series = "GECCO '24",
-
month = "14-18 " # jul,
-
organisation = "SIGEVO",
-
publisher = "Association for Computing Machinery",
-
publisher_address = "New York, NY, USA",
-
keywords = "genetic algorithms, genetic programming, grammatical
evolution, large language models, code generation,
ANN",
-
isbn13 = "979-8-4007-0495-6",
-
DOI = "doi:10.1145/3638530.3664162",
-
size = "8 pages",
-
abstract = "Code generation is one of the most valuable
applications of AI, as it allows for automated
programming and {"}self-building{"} programs. Both
Large Language Models (LLMs) and evolutionary methods,
such as Genetic Programming (GP) and Grammatical
Evolution (GE), are known to be capable of performing
code generation with reasonable performance. However,
to the best of our knowledge, little work has been done
so far on a systematic comparison between the two
approaches. Most importantly, the only studies that
conducted such comparisons used benchmarks from the GP
community, which, in our opinion, may have provided
possibly GP-biased results. In this work, we perform a
comparison of LLMs and evolutionary methods, in
particular GE, using instead a well-known benchmark
originating from the LLM community. Our results show
that, in this scenario, LLMs can solve significantly
more tasks than GE, indicating that GE struggles to
match the performance of LLMs on code generation tasks
that have different properties from those commonly used
in the GP community.",
-
notes = "GECCO-2024 LLMfwEC A Recombination of the 33rd
International Conference on Genetic Algorithms (ICGA)
and the 29th Annual Genetic Programming Conference
(GP)",
- }
Genetic Programming entries for
Leonardo Lucio Custode
Chiara Camilla Migliore Rambaldi
Marco Roveri
Giovanni Iacca
Citations