Recent advances in deep learning have improved the performance of many Natural
Language Processing (NLP) tasks such as translation, question-answering, and text …

Integrating free-text explanations to in-context learning of large language models (LLM) is
shown to elicit strong reasoning capabilities along with reasonable explanations. In this …

Existing work on augmenting question answering (QA) models with external knowledge (eg,
knowledge graphs) either struggle to model multi-hop relations efficiently, or lack …

Pre-trained language models (PTLM) have achieved impressive results in a range of natural
language understanding (NLU) and generation (NLG) tasks. However, current pre-training …

Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained
language models have shown limited capabilities of acquiring implicit commonsense …

Much research effort has been put to multilingual knowledge graph (KG) embedding
methods to address the entity alignment task, which seeks to match entities in different …

Answering complex questions often requires reasoning over knowledge graphs (KGs). State-
of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are …

Recent pre-trained language models (PLMs) equipped with foundation reasoning skills
have shown remarkable performance on downstream complex tasks. However, the …

Commonsense question answering (QA) requires machines to utilize the QA content and
external commonsense knowledge graph (KG) for reasoning when answering questions …

Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted
increasing attention, showing promising performance in many knowledge-intensive tasks …