24 papers · ranked by Valyu relevance
Jingde Cheng
— Recently, with the application progress of AIGC tools based on large language models (LLMs), led by ChatGPT, many AI experts and more non-professionals are trumpeting the "reasoning ability" of the LLMs. The present author considers that the so-called "reasoning ability" of LLMs are just illusions of those people who…
Xinyu Pi, Wanjun Zhong, Yan Gao, Nan Duan + 1 more
We present LogiGAN, an unsupervised adversarial pre-training framework for improving logical reasoning abilities of language models. Upon automatic identification of logical reasoning phenomena in massive text corpus via detection heuristics, we train language models to predict the masked-out logical statements.…
Siyuan Wang, Wanjun Zhong, Duyu Tang, Zhongyu Wei + 4 more
'Daxin Jiang' 'Ming Zhou' 'Nan Duan'] Logical reasoning of text requires understanding critical logical information in the text and performing inference over them. Largescale pre-trained models for logical reasoning mainly focus on word-level semantics of text while struggling to capture symbolic logic. In this paper…
Ehsan Latif, Yifan Zhou, Shuchen Guo, Yizhu Gao + 5 more
This study evaluates the performance of OpenAI’s o1-preview model in higher-order cognitive domains, including critical thinking, systematic thinking, computational thinking, data literacy, creative thinking, logical reasoning, and scientific reasoning. Using established benchmarks, we compared the o1-preview models’…
Authors not listed
Step-by-step thinking is essential in all domains of chemical sciences and engineering. While machine learning tools are broadly used, algorithms that automate reasoning are far less common. We elaborate on seven categories of human reasoning activities and connect each to applications in chemical science and…
Seunghyun Park, Yuanyuan Lei
While LLMs demonstrate impressive reasoning capabilities, they remain fragile in multi-step logical deduction, where a single transition error can propagate through the entire reasoning chain, leading to unstable performance. In this work, we identify logical connectives as primary points of this structural fragility.…
Zhang, Yunyao, Zhang, Xinglang + 12 more
Logical reasoning is a fundamental capability of large language models (LLMs). However, existing studies largely overlook the interplay between logical complexity and semantic complexity, resulting in methods that struggle to address challenging scenarios involving abstract propositions, ambiguous contexts, and…
Antigoni Belekou, Charalabos Papageorgiou, Efstratios Karavasilis, Eleftheria Tsaltas + 3 more
Paradoxes are a special form of reasoning leading to absurd inferences in contrast to logical reasoning that is used to reach valid conclusions. A functional MRI (fMRI) study was conducted to investigate the neural substrates of paradoxical and deductive reasoning. Twenty-four healthy participants were scanned using…
Hope Kean, Alexander Fung, Paris Jaggers, Jason Chen + 6 more
Humans are endowed with a powerful capacity for both inductive and deductive logical thought: we easily form generalizations based on a few examples and draw conclusions from known premises. Humans also arguably have the most sophisticated communication system in the animal kingdom: natural language allows us to…
Wesley H. Holliday, Matthew Mandelkern
The reasoning abilities of large language models (LLMs) are the topic of a growing body of research in AI and cognitive science. In this paper, we probe the extent to which twenty-nine LLMs are able to distinguish logically correct inferences from logically fallacious ones. We focus on inference patterns involving…
Hope Kean, Alexander Fung, Paris Jaggers, Jason Chen + 6 more
Humans are endowed with a powerful capacity for both inductive and deductive logical thought: we easily form generalizations based on a few examples and draw conclusions from known premises. Humans also arguably have the most sophisticated communication system in the animal kingdom: natural language allows us to…
Ana Martín-Salguero, Carlo Reverberi, Aldo Solari, Luca Filippin + 2 more
'Christophe Pallier' 'Luca L. Bonatti'] We often express our thoughts through words, but thinking goes well beyond language. Here we focus on an elementary but basic thinking process, disjunction elimination, elicited by elementary visual scenes deprived of linguistic content, describing its neural and oculomotor…
Andrew K Lampinen, Ishita Dasgupta, Stephanie C Y Chan, Hannah R Sheahan + 5 more
'Hannah R Sheahan' 'Antonia Creswell' 'Dharshan Kumaran' 'James L McClelland' 'Felix Hill' 'Derek Abbott'] Title: Abstract Abstract reasoning is a key ability for an intelligent system. Large language models (LMs) achieve above-chance performance on abstract reasoning tasks but exhibit many imperfections. However…
Jian He, Feng Lu
Reasoning Authors: ['Jian He' 'Feng Lu'] Large language models (LLMs) have been utilized in solving diverse reasoning tasks, encompassing common sense, arithmetic and deduction tasks. However, with difficulties of reversing thinking patterns and irrelevant premises, how to determine the authenticity of the cause in…
Omid Ghasemi, Simon J. Handley, Rachel G. Stephens
When individuals are asked to evaluate the believability of the conclusions to valid or invalid arguments, they often endorse valid conclusions at higher rates than invalid ones. This effect of validity on belief judgments-the “logic-belief effect” -is considered evidence of intuitive logic. However, recent studies…
Yun-Fei Liu, Marina Bedny
Programming is a cornerstone of modern society, yet its cognitive and neural basis remains poorly understood. In this study, we test the hypothesis that programming “recycles” pre-existing neural mechanisms and representations in fronto-parietal reasoning networks. Using fMRI, we scanned programming-naïve…
Dániel Rivas-Blanco, Marco Vasconcelos, Friederike Range, Alex Kacelnik + 1 more
We critically examine theoretical and experimental evidence that animals’ reason by exclusion, focusing on a widespread protocol known as the 2-Cups Task. We test the hypothesis that subjects solve inference by exclusion tasks by responding independently to two options, without implementing complex reasoning, as…
Dániel Rivas-Blanco, Marco Vasconcelos, Friederike Range, Alex Kacelnik + 1 more
Is human language necessary for logical reasoning? Multiple studies address this by showing animals a bait hidden in either of two inverted cups, briefly lifting one exposing its content and then letting subjects choose. Consistent preference for the baited container is interpreted as evidence of inferential reasoning…
Authors not listed
Artificial intelligence, represented by large language models (LLMs), has demonstrated tremendous capabilities in natural language recognition and extraction. To further evaluate the performance of various LLMs in extracting information from academic papers, this study explores the application of LLMs in reticular…
Authors not listed
In the real world, many reversal phenomena occur—for example, cases in which a statement once regarded as false is later recognized as true. Upside-Down Logic is a framework designed to formalize such reversal phenomena as a logical system. It inverts the truth and falsity of propositions through contextual…
Authors not listed
In philosophy and science, a first principle is a basic proposition or assumption that cannot be deduced from any other proposition or assumption. Ancient Greek philosophy Aristotle defined the first principle as “the first basis from which a thing is known.” First principles thinking (or reasoning from first…
Tianfan Jin, Brett M Savoie
Contemporary machine learning algorithms have largely succeeded in automating the development of mathematical models from data. Although this is a striking accomplishment, it leaves unaddressed the multitude of scenarios, especially across the chemical sciences and engineering, where deductive, rather than inductive…
Authors not listed
Nuclear Magnetic Resonance (NMR) structure determination is an important problem in education, industry, and research. Solving NMR spectra requires expert knowledge, critical thinking, and careful evaluation of multiple features of spectral data. This study explores the capabilities of large language models (LLMs) for…
Authors not listed
The scarcity and expense of fatigue data limits optimal design of components and constrains companies to a few well qualified materials when safety-critical applications are concerned. This research investigates different strategies to improve extraction of structured information from unstructured scientific…