Language models (LMs) have demonstrated remarkable capabilities across a wide range of
tasks in various domains. Despite their impressive performance, the reliability of their output …

The increased deployment of LMs for real-world tasks involving knowledge and facts makes
it important to understand model epistemology: what LMs think they know, and how their …

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 …

Neural sequence generation models are known to “hallucinate”, by producing outputs that
are unrelated to the source text. These hallucinations are potentially harmful, yet it remains …

In selective prediction, a classifier is allowed to abstain from making predictions on low-
confidence examples. Though this setting is interesting and important, selective prediction …

Despite efforts to expand the knowledge of large language models (LLMs), knowledge gaps-
-missing or outdated information in LLMs--might always persist given the evolving nature of …

A well-calibrated neural model produces confidence (probability outputs) closely
approximated by the expected accuracy. While prior studies have shown that mixup training …

Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names.
Most of the exciting studies in neural machine translation (NMT) are focused on tackling …

Modern neural machine translation (NMT) models have achieved competitive performance
in standard benchmarks such as WMT. However, there still exist significant issues such as …

Self-training has proven effective for improving NMT performance by augmenting model
training with synthetic parallel data. The common practice is to construct synthetic data …