Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Weyssow, Martin"'
Evaluating the alignment of large language models (LLMs) with user-defined coding preferences is a challenging endeavour that requires a deep assessment of LLMs' outputs. Existing methods and benchmarks rely primarily on automated metrics and static
Externí odkaz:
http://arxiv.org/abs/2403.09032
Motivated by recent work on lifelong learning applications for language models (LMs) of code, we introduce CodeLL, a lifelong learning dataset focused on code changes. Our contribution addresses a notable research gap marked by the absence of a long-
Externí odkaz:
http://arxiv.org/abs/2312.12492
Large Language Models (LLMs) demonstrate impressive capabilities to generate accurate code snippets given natural language intents in zero-shot, i.e., without the need for specific fine-tuning. While prior studies have highlighted the advantages of f
Externí odkaz:
http://arxiv.org/abs/2308.10462
Publikováno v:
ESEC/FSE 2023
Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream tasks. Howe
Externí odkaz:
http://arxiv.org/abs/2305.04106
The objective of pre-trained language models is to learn contextual representations of textual data. Pre-trained language models have become mainstream in natural language processing and code modeling. Using probes, a technique to study the linguisti
Externí odkaz:
http://arxiv.org/abs/2206.11719
Publikováno v:
44th International Conference on Software Engineering, 2022, New Ideas and Emerging Results (ICSE-NIER)
The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approaches based on state-of-the-art model architectures. Nevertheless, we believe that the current state-of-the-art d
Externí odkaz:
http://arxiv.org/abs/2201.03346
Publikováno v:
Software and Systems Modeling, 2022
The design of conceptually sound metamodels that embody proper semantics in relation to the application domain is particularly tedious in Model-Driven Engineering. As metamodels define complex relationships between domain concepts, it is crucial for
Externí odkaz:
http://arxiv.org/abs/2104.01642
Autor:
Weyssow, Martin1 (AUTHOR) martin.weyssow@umontreal.ca, Sahraoui, Houari1 (AUTHOR), Syriani, Eugene1 (AUTHOR)
Publikováno v:
Software & Systems Modeling. Jun2022, Vol. 21 Issue 3, p1071-1089. 19p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.