The task of repository-level code completion is to continue writing the
...
We systematically study the capacity of two large language models for co...
Pre-trained language models have achieved promising success in code retr...
Fine-tuning large language models for different tasks can be costly and
...
DBSCAN has been widely used in density-based clustering algorithms. Howe...
Integrating free-text explanations to in-context learning of large langu...
The information in tables can be an important complement to text, making...
Dialog response generation in open domain is an important research topic...
Summarizing sales calls is a routine task performed manually by salespeo...
Knowledge-grounded dialogue systems are challenging to build due to the ...
Large pretrained generative models like GPT-3 often suffer from hallucin...
The paper estimates the need for additional attorney hours annually to
a...
Transformers have outperformed recurrent neural networks (RNNs) in natur...
In this work, we aim at equipping pre-trained language models with struc...
Self-attention mechanisms have achieved great success on a variety of NL...
In this work, we present X-SQL, a new network architecture for the probl...
We present a sequence-to-action parsing approach for the natural languag...
We consider the problem of neural semantic parsing, which translates nat...
Policy gradient methods have achieved remarkable successes in solving
ch...
High dimensional structured data such as text and images is often poorly...
Incorporating domain knowledge into the modeling process is an effective...