Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

As a main field of artificial intelligence, natural language processing (NLP) has achieved
remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in …

A prominent weakness of modern language models (LMs) is their tendency to generate
factually incorrect text, which hinders their usability. A natural question is whether such …

Language models are trained on large volumes of text, and as a result their parameters
might contain a significant body of factual knowledge. Any downstream task performed by …

Pre-trained language models (PLMs) are known to improve the generalization performance
of natural language understanding models by leveraging large amounts of data during the …

Pre-trained language models (PLMs) have gained increasing popularity due to their
compelling prediction performance in diverse natural language processing (NLP) tasks …

Trustworthy language models should abstain from answering questions when they do not
know the answer. However, the answer to a question can be unknown for a variety of …

Abstract Despite advances in Visual Question Answering (VQA), the ability of models to
assess their own correctness remains underexplored. Recent work has shown that VQA …

Abstract Machine learning has advanced dramatically, narrowing the accuracy gap to
humans in multimodal tasks like visual question answering (VQA). However, while humans …

Chat-based language models are designed to be helpful, yet they should not comply with
every user request. While most existing work primarily focuses on refusal of" unsafe" …