A5100763686- Topic Modeling
- Natural Language Processing Techniques
- Advancements in Battery Materials
- Explainable Artificial Intelligence (XAI)
- Advanced Graph Neural Networks
- Advanced Battery Materials and Technologies
- Advanced Battery Technologies Research
- Bayesian Modeling and Causal Inference
- Data Quality and Management
- Robotic Path Planning Algorithms
- Supercapacitor Materials and Fabrication
- Multimodal Machine Learning Applications
- Metaheuristic Optimization Algorithms Research
- Ethics in Business and Education
- Human Pose and Action Recognition
- Advanced Computational Techniques and Applications
- Face and Expression Recognition
- Interactive and Immersive Displays
- Catalytic Processes in Materials Science
- Target Tracking and Data Fusion in Sensor Networks
- Reinforcement Learning in Robotics
- Text Readability and Simplification
- Sparse and Compressive Sensing Techniques
- Advancements in Solid Oxide Fuel Cells
- Advanced Computing and Algorithms
Shanghai Jiao Tong University
2024
Shenzhen Academy of Metrology and Quality Inspection
2024
Harbin Institute of Technology
2012-2023
Jingdong (China)
2021
Wuhan Engineering Science & Technology Institute
2020
Northwestern Polytechnical University
2016
Zhejiang University
2015
Southwest University of Science and Technology
2014
Shanghai Maritime University
2011
Polytechnic University of Turin
2011
Large language models (LLMs) have shown great potential across various industries due to their remarkable ability generalize through instruction tuning. However, the limited availability of domain-specific data significantly hampers performance on specialized tasks. While existing methods primarily focus selecting training from general datasets that are similar target domain, they often fail consider joint distribution instructions, resulting in inefficient learning and suboptimal knowledge...
Understanding causality has vital importance for various Natural Language Processing (NLP) applications. Beyond the labeled instances, conceptual explanations of can provide deep understanding causal fact to facilitate reasoning process. However, such explanation information still remains absent in existing resources. In this paper, we fill gap by presenting a human-annotated explainable CAusal REasoning dataset (e-CARE), which contains over 20K questions, together with natural language...
Fraud activities in e-commerce, such as spam reviews and fake shopping behaviors, significantly mislead customers' decision making, damage the platforms' reputation, reduce enterprises' revenue. In recent years, GNN-based models have been widely adopted fraud detection tasks, which shown better performance compared to conventional rule-based methods feature-based models. Most focus on homogeneous graphs, usually including user-to-user, or item-to-item connections. These types of graphs...
Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin. Proceedings of the 59th Annual Meeting Association for Computational Linguistics and 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face inconsistency issues. Existing works primarily focus on the issues within a single LLM, while we complementarily explore inter-consistency among multiple LLMs for collaboration. To examine whether can collaborate effectively to achieve consensus shared goal, commonsense reasoning, and introduce formal debate framework (FORD) conduct three-stage with real-world scenarios alignment:...
We focus on the task of stock market prediction based financial text which contains information that could influence movement market. Previous works mainly utilize a single semantic unit text, such as words, events, sentences, to predict tendency However, interaction different-grained within can be useful for context knowledge supplement and predictive selection, then improve performance prediction. To facilitate this, we propose constructing heterogeneous graph with nodes from task. A novel...
Quantum genetic algorithm is a recently proposed new optimization combining quantum with algorithm. It characterizes good population diversity, rapid convergence and global search capability so attracts serious wide attentions. This paper proposes novel called variable-boundary-coded (vbQGA) in which qubit chromosomes are collapsed into instead of binary-coded chromosomes. In this way we can obtain much shorter chromosome strings. The method encoding decoding first described before adaptive...
Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face inconsistency issues. Existing works primarily focus on the issues within a single LLM, while we complementarily explore inter-consistency among multiple LLMs for collaboration. To examine whether can collaborate effectively to achieve consensus shared goal, commonsense reasoning, and introduce formal debate framework (FORD) conduct three-stage with real-world scenarios alignment:...
Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting pairs. However, CCR suffers from two main transitive problems: threshold effect and scene drift. In other words, pairs be spliced may have a conflicting boundary or scenario.To address these issues, we propose novel Reliable framework (ReCo), introduces exogenous variables represent factors of each pair within chain, estimates...
Through pretraining on a corpus with various sources, Large Language Models (LLMs) have gained impressive performance. However, the impact of each component remains opaque. As result, organization is still empirical and may deviate from optimal. To address this issue, we systematically analyze 48 datasets 5 major categories data LLMs measure their impacts using benchmarks about nine model capabilities. Our analyses provide results contribution multiple corpora performances LLMs, along joint...
Large language models (LLMs) have developed impressive performance and strong explainability across various reasoning scenarios, marking a significant stride towards mimicking human-like intelligence. Despite this, when tasked with simple questions supported by generic fact, LLMs often fail to provide consistent precise answers, indicating deficiency in abstract abilities. This has sparked vigorous debate about whether are genuinely or merely memorizing. In light of we design preliminary...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Highly accurate measurements of the entropic coefficient lithium-ion batteries (LIBs) over a wide state-of-charge (SoC) range are essential for optimizing thermal management systems used to maintain battery temperature within an appropriate level, and thereby limit aging process avoid runaway, which can lead fire or explosions. This is usually accomplished by potentiometric method. However, high time consumption this method greatly limits its usefulness in commercial settings. The present...
Highly accurate measurements of the entropic coefficient lithium-ion batteries (LIBs) are essential for optimizing thermal management systems. This is usually accomplished by potentiometric method. However, high time consumption this method greatly limits its usefulness in commercial settings. The present work addresses issue proposing a fast and precise to determine coefficients LIBs based on frequency-domain analysis. continuous profile LiFePO4/Graphite prismatic cell measured. analysis...
Though demonstrating promising potential, LLMs' performance on complex tasks, such as advanced mathematics and disease diagnosis is still unsatisfactory. A key issue the present LLMs learn in a data-driven schema, while instruction dataset about these tasks both scarce hard to collect or construct. On contrary, prominent phenomenon that can rather fast those simpler with adequate prior knowledge captured during pretraining stage. Thus, if prerequisite mechanism of rapid generalization could...