As NLP models achieved state-of-the-art performances over benchmarks and gained wide
applications, it has been increasingly important to ensure the safe deployment of these …

Dense retrieval (DR) methods conduct text retrieval by first encoding texts in the embedding
space and then matching them by nearest neighbor search. This requires strong locality …

Abstract Machine learning (ML) systems in natural language processing (NLP) face
significant challenges in generalizing to out-of-distribution (OOD) data, where the test …

Prompt-based learning (aka prompting) achieves high performance by bridging the gap
between the objectives of language modeling and downstream tasks. Domain …

Large pretrained language models are critical components of modern NLP pipelines. Yet,
they suffer from spurious correlations, poor out-of-domain generalization, and biases …

Abstract Domain adaptation aims to transfer the knowledge learned on (data-rich) source
domains to (low-resource) target domains, and a popular method is invariant representation …

There has been mounting evidence that pretrained language models fine-tuned on large
and diverse supervised datasets can transfer well to a variety of out-of-domain tasks. In this …

Transformer-based language models (TLMs), such as BERT, ALBERT and GPT-3, have
shown strong performance in a wide range of NLP tasks and currently dominate the field of …

The ability of deep neural networks to generate state-of-the-art results on many NLP
problems has been apparent to everyone for some years now. However, when there is not …

Although instruction tuning is widely used to adjust behavior in Large Language Models
(LLMs), extensive empirical evidence and research indicates that it is primarily a process …