Search Results for author:
Found 7 papers, 4 papers with code
CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences
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.
CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code
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.
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models
In this paper, we deliver a comprehensive study of PEFT techniques for LLMs under the automated code generation scenario.
On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code
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.
AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models
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.
Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning
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.
Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models
The design of conceptually sound metamodels that embody proper semantics in relation to the application domain is particularly tedious in Model-Driven Engineering.
