26 papers · ranked by Valyu relevance
Pranav Punuru, Nabil Ibtehaz, Swagarika Giri, Harsha Srirangam + 2 more
The rapid expansion of biomedical literature has made comprehensive manual synthesis increasingly difficult to perform effectively, creating a pressing need for AI systems capable of reasoning across verified evidence rather than merely retrieving it. However, existing retrieval-augmented generation (RAG) methods often…
Felix Faltings, Wei Wei, Yujia Bao
Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle complex queries involving logical constructs such as negations, conjunctions, and…
Jiaxin Bai, Luo Chen, Zheng Li, Qingyu Yin + 2 more
Jiaxin Bai, Chen Luo, Zheng Li, Qingyu Yin, Bing Yin, and Yangqiu Song. 2023. Knowledge Graph Reasoning over Entities and Numerical Values. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '23), August 6–10, 2023, Long Beach, CA, USA. ACM, New York, NY, USA, 12 pages.…
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…
Zhicheng Lee, Shulin Cao, Jinxin Liu, Jiajie Zhang + 4 more
'Xiaoyin Che' 'Lei Hou' 'Juanzi Li'] Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works adopt reinforcement learning (RL) training to integrate reasoning with retrieval, such methods are often complex and…
Reto Gubelmann
Taking Leibniz' ideal of a universal truth-calculating machine as a vantage point, this article provides a philosophically sound analysis of the concept of reasoning in NLP. It argues that reasoning always involves inference, which in turn requires being guided by reason relations. Based on this, the article argues…
Jia Xu, Patrick Shironoshita, Ubbo Visser, Nigel John + 1 more
'Mansur Kabuka'] Efficiently querying Description Logic (DL) ontologies is becoming a vital task in various data-intensive DL applications. Considered as a basic service for answering object queries over DL ontologies, instance checking can be realized by using the most specific concept (MSC) method, which converts…
Amin Mobasheri
Finding relevant geospatial information is increasingly critical because of the growing volume of geospatial data available within the emerging “Big Data” era. Users are expecting that the availability of massive datasets will create more opportunities to uncover hidden information and answer more complex queries. This…
Douglas Summers-Stay
Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in such a vector space, combining analogy, association, and deduction in a…
Zezhong Xu, Peng Ye, Lei Liang, Huajun Chen + 1 more
Answering logical queries on knowledge graphs (KG) poses a significant challenge for machine reasoning. The primary obstacle in this task stems from the inherent incompleteness of KGs. Existing research has predominantly focused on addressing the issue of missing edges in KGs, thereby neglecting another aspect of…
Luke J. Hearne, Conor Robinson, Luca Cocchi, Takuya Ito
Relational reasoning—the capacity to understand how elements relate to one another—is a defining feature of human intelligence, yet its computational basis remains unclear. Here, we combined human neuroimaging (7T fMRI) and artificial neural network modeling to examine relational reasoning in biological and artificial…
Xingrui Zhuo, Jiapu Wang, Gongqing Wu, Shirui Pan + 1 more
on Knowledge Graphs Authors: ['Xingrui Zhuo' 'Jiapu Wang' 'Gongqing Wu' 'Shirui Pan' 'Xindong Wu'] Xingrui Zhuo, Jiapu Wang, Gongqing Wu, Shirui Pan, and Xindong Wu. 2024. Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs. In Proceedings of Make sure to enter the correct…
Liena Hačatrjana, Dace Namsone
Various skills related to critical thinking, reasoning, and scientific reasoning are defined as essential for students in policy documents and curricula around the world as essential both in school and in everyday life. However, these concepts are often too vaguely defined and explained for a clear implementation in…
Seokjun Lee, Incheol Kim
Service robots operating in indoor environments should recognize dynamic changes from sensors, such as RGB-depth (RGB-D) cameras, and recall the past context. Therefore, we propose a context query-processing framework, comprising spatio-temporal robotic context query language (ST-RCQL) and a spatio-temporal robotic…
Shihua Zhao, Yuqing Yang, Zilong Wang, Zhiyuan He + 2 more
on How to Make your LLMs use External Data More Wisely Authors: ['Shihua Zhao' 'Yuqing Yang' 'Zilong Wang' 'Zhiyuan He' 'Liangfei Qiu' 'Lili Qiu'] Large language models (LLMs) augmented with external data have demonstrated remarkable capabilities in completing real-world tasks. External data not only bolsters the…
Leonardo Ranaldi, Marco Valentino, Alexander Polonsky, Andrè Freitas
Chain-of-Though (CoT) represents a common strategy for reasoning in Large Language Models (LLMs) by decomposing complex tasks into intermediate inference steps. However, explanations generated via CoT are susceptible to content biases that negatively affect their robustness and faithfulness. To mitigate existing…
Yongyue Wang, Beitong Yao, Tianbo Wang, Chunhe Xia + 1 more
Modern retrieval systems tend to deteriorate because of their large output of useless and even misleading information, especially for complex search requests on a large scale. Complex information retrieval (IR) tasks requiring multi-hop reasoning need to fuse multiple scattered text across two or more documents.…
Ling Cai, Krzysztof Janowicz, Rui Zhu, Gengchen Mai + 2 more
Qualitative spatial/temporal reasoning (QSR/QTR) plays a key role in research on human cognition, e.g., as it relates to navigation, as well as in work on robotics and artificial intelligence. Although previous work has mainly focused on various spatial and temporal calculi, more recently representation learning…
Yichun Feng, Lu Zhou, Yikai Zheng, Ruikun He + 2 more
In recent years, Large Language Models (LLMs) have shown promise in various domains, notably in biomedical sciences. However, their real-world application is often limited by issues like erroneous outputs and hallucinatory responses. We developed the Knowledge Graph-based Thought (KGT) framework, an innovative solution…
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 Socratic method, grounded in iterative questioning and critical dialogue, offers a compelling framework for leveraging large language models (LLMs) to advance scientific reasoning and discovery in chemistry and materials science. In this paper, we explore how Socratic principles can be integrated into prompt…
Helia Mohammadi, Fatemeh Almodaresi, Gregory F J Hogue, Adam Wright + 4 more
The Reactome Pathway Knowledgebase (www.reactome.org) provides expert-curated information on human biological pathways, molecular interactions, and disease mechanisms. However, its complex data model and keyword-based search interface present accessibility barriers for non-expert users. In contrast, general-purpose…
Ishita Dasgupta, Eric Schulz, Joshua B. Tenenbaum, Samuel J. Gershman
Bayesian theories of cognition assume that people can integrate probabilities rationally. However, several empirical findings contradict this proposition: human probabilistic inferences are prone to systematic deviations from optimality. Puzzlingly, these deviations sometimes go in opposite directions. Whereas some…
Authors not listed
Agentic artificial intelligence (AI) is poised to redefine how science is conducted, automating not just data analysis but the entire research lifecycle, from hypothesis generation to validation. Yet most current AI agents remain domain-bound, tailored to specific applications such as materials synthesis or quantum…
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
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…