2 code implementations • 14 Mar 2024 • Martin Weyssow, Aton Kamanda, Houari Sahraoui
We generate responses to the instructions using a pool of 14 diverse LLMs, which we then annotate according to their alignment with five coding preferences using the LLM-as-a-Judge approach with GPT-3. 5, producing both numerical and textual feedback.
1 code implementation • 20 Dec 2023 • Martin Weyssow, Claudio Di Sipio, Davide Di Ruscio, Houari Sahraoui
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.
1 code implementation • 21 Aug 2023 • Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari Sahraoui
In this paper, we deliver a comprehensive study of PEFT techniques for LLMs under the automated code generation scenario.
no code implementations • 6 May 2023 • Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari Sahraoui
We demonstrate that the most commonly used fine-tuning technique from prior work is not robust enough to handle the dynamic nature of APIs, leading to the loss of previously acquired knowledge i. e., catastrophic forgetting.
no code implementations • 23 Jun 2022 • José Antonio Hernández López, Martin Weyssow, Jesús Sánchez Cuadrado, Houari Sahraoui
Using probes, a technique to study the linguistic properties of hidden vector spaces, previous works have shown that these pre-trained language models encode simple linguistic properties in their hidden representations.
no code implementations • 10 Jan 2022 • Martin Weyssow, Houari Sahraoui, Bang Liu
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.
3 code implementations • 4 Apr 2021 • Martin Weyssow, Houari Sahraoui, Eugene Syriani
The design of conceptually sound metamodels that embody proper semantics in relation to the application domain is particularly tedious in Model-Driven Engineering.