Recently, there has been a surge of interest in the NLP community on the use of pretrained
Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs …

This survey paper proposes a clearer view of natural language reasoning in the field of
Natural Language Processing (NLP), both conceptually and practically. Conceptually, we …

Large language models (LLMs) have been shown to be capable of impressive few-shot
generalisation to new tasks. However, they still tend to perform poorly on multi-step logical …

Abstract Transformers are Deep Neural Networks (DNN) that utilize a self-attention
mechanism to capture contextual relationships within sequential data. Unlike traditional …

Transformers have been shown to emulate logical deduction over natural language theories
(logical rules expressed in natural language), reliably assigning true/false labels to …

Our goal, in the context of open-domain textual question-answering (QA), is to explain
answers by showing the line of reasoning from what is known to the answer, rather than …

We propose a synthetic reasoning task, LEGO (Learning Equality and Group Operations),
that encapsulates the problem of following a chain of reasoning, and we study how the …

Theorem proving in natural mathematical language–the mixture of symbolic and natural
language used by humans–plays a central role in mathematical advances and education …

While large language models (LLMs) have shown remarkable effectiveness in various NLP
tasks, they are still prone to issues such as hallucination, unfaithful reasoning, and toxicity. A …

Recent years have seen impressive performance of transformer-based models on different
natural language processing tasks. However, it is not clear to what degree the transformers …