Large-scale generative models show an impressive ability to perform a wide range of
Natural Language Processing (NLP) tasks using in-context learning, where a few examples …

The task of repository-level code completion is to continue writing the unfinished code based
on a broader context of the repository. While for automated code completion tools, it is …

With direct access to human-written reference as memory, retrieval-augmented generation
has achieved much progress in a wide range of text generation tasks. Since better memory …

ABSTRACT Large Language Models (LLM) are a new class of computation engines,
łprogrammedž via prompt engineering. Researchers are still learning how to best łprogramž …

Large Language Models (LLM) are a new class of computation engines," programmed" via
prompt engineering. Researchers are still learning how to best" program" these LLMs to …

Large language models have demonstrated the capability to perform on machine translation
when the input is prompted with a few examples (in-context learning). Translation quality …

This paper describes our system for the low-resource domain adaptation track (Track 3) in
Spoken Language Understanding Grand Challenge, which is a part of ICASSP Signal …

Modern ML systems increasingly augment input instances with additional relevant
information to enhance final prediction. Despite growing interest in such retrieval …

In few-shot learning, such as meta-learning, few-shot fine-tuning or in-context learning, the
limited number of samples used to train a model have a significant impact on the overall …

Repository-level code generation task involves generating code at a specified location
based on unfinished code with repository context. Existing research mainly rely on retrieval …