In recent years, considerable research has been dedicated to the application of neural
models in the field of natural language generation (NLG). The primary objective is to …

ChatGPT is a powerful artificial intelligence (AI) language model that has demonstrated
significant improvements in various natural language processing (NLP) tasks. However, like …

Vision Language Models (VLMs) are rapidly advancing in their capability to answer
information-seeking questions. As these models are widely deployed in consumer …

Large-scale natural language processing models have been developed and integrated into
numerous applications, given the advantage of their remarkable performance. Nonetheless …

Large language models (LLMs) are often trained on extensive, temporally indiscriminate text
corpora, reflecting the lack of datasets with temporal metadata. This approach is not aligned …

User-generated content provides a rich resource to study social and behavioral phenomena.
Although its application potential is currently limited by the paucity of expert labels and the …

Increasing concerns about privacy leakage issues in academia and industry arise when
employing NLP models from third-party providers to process sensitive texts. To protect …

Human-centered techniques have become integral towards the rapid adoption and
interaction of dialog systems. Despite this, most dialog system designs entail sparse human …

The increasing usage of AI in high-stakes decision-making underscores a pressing need for
various stakeholders to understand AI, learn how to identify AI-generated content, and …

The studies in this thesis aim to address overarching challenges persisting across Natural
Language Generation (NLG) applications, including (1) Limitations in effectively …