Nphardeval: Dynamic benchmark on reasoning ability of large language models via complexity classes

L Fan, W Hua, L Li, H Ling, Y Zhang - arXiv preprint arXiv:2312.14890, 2023 - arxiv.org
Complex reasoning ability is one of the most important features of current LLMs, which has
also been leveraged to play an integral role in complex decision-making tasks. Therefore …

Counterfactual collaborative reasoning

J Ji, Z Li, S Xu, M Xiong, J Tan, Y Ge, H Wang… - Proceedings of the …, 2023 - dl.acm.org
Causal reasoning and logical reasoning are two important types of reasoning abilities for
human intelligence. However, their relationship has not been extensively explored under …

Explaining competitive-level programming solutions using llms

J Li, S Tworkowski, Y Wu, R Mooney - arXiv preprint arXiv:2307.05337, 2023 - arxiv.org
In this paper, we approach competitive-level programming problem-solving as a composite
task of reasoning and code generation. We propose a novel method to automatically …

Towards building specialized generalist ai with system 1 and system 2 fusion

K Zhang, B Qi, B Zhou - arXiv preprint arXiv:2407.08642, 2024 - arxiv.org
In this perspective paper, we introduce the concept of Specialized Generalist Artificial
Intelligence (SGAI or simply SGI) as a crucial milestone toward Artificial General Intelligence …

Visual agents as fast and slow thinkers

G Sun, M Jin, Z Wang, CL Wang, S Ma, Q Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Achieving human-level intelligence requires refining cognitive distinctions between System
1 and System 2 thinking. While contemporary AI, driven by large language models …

Fuzzy Neural Logic Reasoning for Robust Classification

G Lin, Y Zhang - ACM Transactions on Knowledge Discovery from Data, 2024 - dl.acm.org
The efficacy of neural networks is widely recognized across a multitude of machine learning
tasks, yet their black-box nature impedes the understanding of their decision-making …

Distilling Algorithmic Reasoning from LLMs via Explaining Solution Programs

J Li, R Mooney - arXiv preprint arXiv:2404.08148, 2024 - arxiv.org
Distilling explicit chain-of-thought reasoning paths has emerged as an effective method for
improving the reasoning abilities of large language models (LLMs) across various tasks …

Integrate Learning and Reasoning for Large Language Model and Recommender Systems

J Ji - 2024 - search.proquest.com
In the current era, recommendation systems has become increasingly integral to our daily
lives. Despite the significant advancements in recommendation systems, many models still …

Towards trustworthy recommenders: building explainable and unbiased recommendation systems

Y Hu - 2024 - dr.ntu.edu.sg
The explosively increasing online content, such as exposure on e-commerce platforms (eg,
Amazon and Taobao), makes it very difficult for users to choose suitable items or information …