Reasoning system
View article
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning Open
Visual question answering requires high-order reasoning about an image, which\nis a fundamental capability needed by machine systems to follow complex\ndirectives. Recently, modular networks have been shown to be an effective\nframework fo…
View article
Reasoning about Quantities in Natural Language Open
Little work from the Natural Language Processing community has targeted the role of quantities in Natural Language Understanding. This paper takes some key steps towards facilitating reasoning about quantities expressed in natural language…
View article
Practical Shape: A Theory of Practical Reasoning Open
Jonathan Dancy aims to establish the possibility of reasoning to action, by showing how similar it is to reasoning to belief. He offers a general theory of reasoning, which smoothly admits the differences there may be between the two types…
View article
Characterization inference based on joint-optimization of multi-layer semantics and deep fusion matching network Open
The whole sentence representation reasoning process simultaneously comprises a sentence representation module and a semantic reasoning module. This paper combines the multi-layer semantic representation network with the deep fusion matchin…
View article
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning Open
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 reasoning problems. Here we carry out a comprehensive evaluatio…
View article
Large Language Models Are Reasoning Teachers Open
Recent works have shown that chain-of-thought (CoT) prompting can elicit language models to solve complex reasoning tasks, step-by-step. However, prompt-based CoT methods are dependent on very large models such as GPT-3 175B which are proh…
View article
Reasoning with Language Model is Planning with World Model Open
Large language models (LLMs) have shown remarkable reasoning capabilities, particularly with Chain-of-Thought-style prompts. However, LLMs can still struggle with problems that are easy for humans, such as generating action plans for execu…
View article
Analysis of students’ mathematical reasoning Open
The reasoning is one of the mathematical abilities that have very complex implications. This complexity causes reasoning including abilities that are not easily attainable by students. Similarly, studies dealing with reason are quite diver…
View article
Diagnosis and management of clinical reasoning difficulties: Part I. Clinical reasoning supervision and educational diagnosis Open
There are many obstacles to the timely identification of clinical reasoning difficulties in health professions education. This guide aims to provide readers with a framework for supervising clinical reasoning and identifying the potential …
View article
Continuous Reasoning Open
This paper describes work in continuous reasoning, where formal reasoning about a (changing) codebase is done in a fashion which mirrors the iterative, continuous model of software development that is increasingly practiced in industry. We…
View article
On Proactive, Transparent, and Verifiable Ethical Reasoning for Robots Open
Previous work on ethical machine reasoning has largely been theoretical, and where such systems have been implemented, it has, in general, been only initial proofs of principle. Here, we address the question of desirable attributes for suc…
View article
Complexity-Based Prompting for Multi-Step Reasoning Open
We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences describing intermediate reasoning steps towards…
View article
Meta-analysis: how does posterior parietal cortex contribute to reasoning? Open
Reasoning depends on the contribution of posterior parietal cortex (PPC). But PPC is involved in many basic operations-including spatial attention, mathematical cognition, working memory, long-term memory, and language-and the nature of it…
View article
LARS: A Logic-Based Framework for Analyzing Reasoning over Streams Open
The recent rise of smart applications has drawn interest to logical reasoning over data streams. Different query languages and stream processing/reasoning engines were proposed. However, due to a lack of theoretical foundations, the expres…
View article
Reasoning processes in clinical reasoning: from the perspective of cognitive psychology Open
Clinical reasoning is considered a crucial concept in reaching medical decisions. This paper reviews the reasoning processes involved in clinical reasoning from the perspective of cognitive psychology. To properly use clinical reasoning, o…
View article
Modeling as Scientific Reasoning—The Role of Abductive Reasoning for Modeling Competence Open
While the hypothetico-deductive approach, which includes inductive and deductive reasoning, is largely recognized in scientific reasoning, there is not much focus on abductive reasoning. Abductive reasoning describes the theory-based attem…
View article
Dual processing theory and expertsʼ reasoning: exploring thinking on national multiple-choice questions Open
Background An ongoing debate exists in the medical education literature regarding the potential benefits of pattern recognition (non-analytic reasoning), actively comparing and contrasting diagnostic options (analytic reasoning) or using a…
View article
What is Good Reasoning? Open
What makes the difference between good and bad reasoning? In this paper we defend a novel account of good reasoning—both theoretical and practical—according to which it preserves fittingness or correctness : good reasoning is reasoning whi…
View article
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning Open
Huge language models (LMs) have ushered in a new era for AI, serving as a gateway to natural-language-based knowledge tasks. Although an essential element of modern AI, LMs are also inherently limited in a number of ways. We discuss these …
View article
Faithful Reasoning Using Large Language Models Open
Although contemporary large language models (LMs) demonstrate impressive question-answering capabilities, their answers are typically the product of a single call to the model. This entails an unwelcome degree of opacity and compromises pe…
View article
Advancing clinical reasoning in virtual patients – development and application of a conceptual framework Open
Background: Clinical reasoning is a complex skill students have to acquire during their education. For educators it is difficult to explain their reasoning to students, because it is partly an automatic and unconscious process. Virtual Pat…
View article
Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning Open
Large language models (LLMs) have demonstrated impressive reasoning abilities in complex tasks. However, they lack up-to-date knowledge and experience hallucinations during reasoning, which can lead to incorrect reasoning processes and dim…
View article
An Overview of Knowledge Graph Reasoning: Key Technologies and Applications Open
In recent years, with the rapid development of Internet technology and applications, the scale of Internet data has exploded, which contains a significant amount of valuable knowledge. The best methods for the organization, expression, cal…
View article
Deep Learning-Based Reasoning With Multi-Ontology for IoT Applications Open
In the era of mobile big data, data driven intelligent Internet of Things (IoT) applications are becoming widespread, and knowledge-based reasoning is one of the essential tasks of these applications. While most knowledge-based reasoning w…
View article
Graph Collaborative Reasoning Open
Graphs can represent relational information among entities and graph\nstructures are widely used in many intelligent tasks such as search,\nrecommendation, and question answering. However, most of the graph-structured\ndata in practice suf…
View article
Reasoning Like Program Executors Open
Reasoning over natural language is a long-standing goal for the research community. However, studies have shown that existing language models are inadequate in reasoning. To address the issue, we present POET, a novel reasoning pre-trainin…
View article
An Ontology-Based Reasoning Framework for Querying Satellite Images for Disaster Monitoring Open
This paper presents a framework in which satellite images are classified and augmented with additional semantic information to enable queries about what can be found on the map at a particular location, but also about paths that can be tak…
View article
RAVEN: A Dataset for Relational and Analogical Visual rEasoNing Open
Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and…
View article
Streaming MASSIF: Cascading Reasoning for Efficient Processing of IoT Data Streams Open
In the Internet of Things (IoT), multiple sensors and devices are generating heterogeneous streams of data. To perform meaningful analysis over multiple of these streams, stream processing needs to support expressive reasoning capabilities…
View article
LAMBADA: Backward Chaining for Automated Reasoning in Natural Language Open
Remarkable progress has been made on automated reasoning with natural text, by using Large Language Models (LLMs) and methods such as Chain-of-Thought prompting and Selection-Inference. These techniques search for proofs in the forward dir…