Natural language reasoning, a survey

F Yu, H Zhang, P Tiwari, B Wang - ACM Computing Surveys, 2024 - dl.acm.org
This survey article proposes a clearer view of Natural Language Reasoning (NLR) in the
field of Natural Language Processing (NLP), both conceptually and practically …

Reasoning with language model prompting: A survey

S Qiao, Y Ou, N Zhang, X Chen, Y Yao, S Deng… - arXiv preprint arXiv …, 2022 - arxiv.org
Reasoning, as an essential ability for complex problem-solving, can provide back-end
support for various real-world applications, such as medical diagnosis, negotiation, etc. This …

Improving causal reasoning in large language models: A survey

S Xiong, D Chen, Q Wu, L Yu, Q Liu, D Li… - arXiv preprint arXiv …, 2024 - arxiv.org
Causal reasoning (CR) is a crucial aspect of intelligence, essential for problem-solving,
decision-making, and understanding the world. While large language models (LLMs) can …

Logical reasoning over natural language as knowledge representation: A survey

Z Yang, X Du, R Mao, J Ni, E Cambria - arXiv preprint arXiv:2303.12023, 2023 - arxiv.org
Logical reasoning is central to human cognition and intelligence. It includes deductive,
inductive, and abductive reasoning. Past research of logical reasoning within AI uses formal …

Large language models are not strong abstract reasoners

G Gendron, Q Bao, M Witbrock, G Dobbie - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models have shown tremendous performance on a large variety of natural
language processing tasks, ranging from text comprehension to common sense reasoning …

tasksource: A large collection of nlp tasks with a structured dataset preprocessing framework

D Sileo - Proceedings of the 2024 Joint International Conference …, 2024 - aclanthology.org
Abstract The HuggingFace Datasets Hub hosts thousands of datasets, offering exciting
opportunities for language model training and evaluation. However, datasets for a specific …

LogicNet: A Logical Consistency Embedded Face Attribute Learning Network

H Wu, S Tian, H Li, KW Bowyer - arXiv preprint arXiv:2311.11208, 2023 - arxiv.org
Ensuring logical consistency in predictions is a crucial yet overlooked aspect in multi-
attribute classification. We explore the potential reasons for this oversight and introduce two …

Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus

T Morishita, G Morio, A Yamaguchi… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) are capable of solving a wide range of tasks, yet they have
struggled with reasoning. To address this, we propose $\textbf {Additional Logic Training …

Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning

Q Bao, AY Peng, Z Deng, W Zhong, G Gendron… - arXiv preprint arXiv …, 2023 - arxiv.org
Combining large language models with logical reasoning enhances their capacity to
address problems in a robust and reliable manner. Nevertheless, the intricate nature of …