A5101074704- Natural Language Processing Techniques
- Topic Modeling
- Microplastics and Plastic Pollution
- biodegradable polymer synthesis and properties
- Crop Yield and Soil Fertility
- Advanced Text Analysis Techniques
- Software Engineering Research
- Laser-Ablation Synthesis of Nanoparticles
- Biomedical Ethics and Regulation
- AI-based Problem Solving and Planning
- Mobile Crowdsensing and Crowdsourcing
- Plant Water Relations and Carbon Dynamics
- Soil and Unsaturated Flow
- Expert finding and Q&A systems
- Food Industry and Aquatic Biology
- Agronomic Practices and Intercropping Systems
- Text Readability and Simplification
- Irrigation Practices and Water Management
- Advanced Sensor Technologies Research
- Advanced Machining and Optimization Techniques
- Spectroscopy and Laser Applications
- Electrohydrodynamics and Fluid Dynamics
- Speech Recognition and Synthesis
- Robot Manipulation and Learning
- Plant nutrient uptake and metabolism
Sichuan University
2018
Shandong Agricultural University
2017
Despite the advancements of open-source large language models (LLMs), e.g., LLaMA, they remain significantly limited in tool-use capabilities, i.e., using external tools (APIs) to fulfill human instructions. The reason is that current instruction tuning largely focuses on basic tasks but ignores domain. This contrast excellent capabilities state-of-the-art (SOTA) closed-source LLMs, ChatGPT. To bridge this gap, we introduce ToolLLM, a general framework encompassing data construction, model...
Humans possess an extraordinary ability to create and utilize tools, allowing them overcome physical limitations explore new frontiers. With the advent of foundation models, AI systems have potential be equally adept in tool use as humans. This paradigm, i.e., learning with combines strengths specialized tools models achieve enhanced accuracy, efficiency, automation problem-solving. Despite its immense potential, there is still a lack comprehensive understanding key challenges,...
The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable sophisticated reasoning, robust perception, and versatile action across diverse domains. As these increasingly drive AI research practical applications, their design, evaluation, continuous improvement present intricate, multifaceted challenges. This survey provides comprehensive overview, framing within modular, brain-inspired...
Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou. Proceedings of the 61st Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2023.
Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, they also introduce novel vulnerabilities that demand careful consideration for safety. However, there exists a notable gap the literature, as has been no comprehensive exploration of these vulnerabilities. This position paper fills this thorough...
Plastic film is an important resource in agricultural production, but it takes hundreds of years to degrade completely natural environment. The large-scale use plastic will inevitably lead serious environmental pollution. One way solve the problem develop a substitutable mulching film, such as biodegradable that can ultimately be decomposed water, carbon dioxide, and soil organic matter by micro-organisms. In this study, 2-year experiment was conducted determine degradation properties...
Timely monitoring and regulation of the transport distribution soil water heat are appropriate methods to ensure improve crop yields. With degradation oxo-biodegradable film, upper boundary condition is a time-variable boundary, water-heat more complicated, comparing with conventional plastic film. Based on HYDRUS-2D version 2.02 characteristics mulching films, coupled mathematical model drip irrigation was established, simulated content temperature were tested against three-year field...
Long-form question answering (LFQA) aims at complex, open-ended questions with detailed, paragraph-length responses. The de facto paradigm of LFQA necessitates two procedures: information retrieval, which searches for relevant supporting facts, and synthesis, integrates these facts into a coherent answer. In this paper, we introduce WebCPM, the first Chinese dataset. One unique feature WebCPM is that its retrieval based on interactive web search, engages search engine in real time. Following...
Recent years have witnessed the success of question answering (QA), especially its potential to be a foundation paradigm for tackling diverse NLP tasks. However, obtaining sufficient data build an effective and stable QA system still remains open problem. For this problem, we introduce iterative bootstrapping framework augmentation (named QASnowball), which can iteratively generate large-scale high-quality based on seed set supervised examples. Specifically, QASnowball consists three...
Plastic film is an important resource in agricultural production, but it takes hundreds of years to degrade completely natural environment. The large-scale use plastic will inevitably lead serious environmental pollution. One way solve the problem develop a substitutable mulching film, such as biodegradable film that can ultimately be decomposed water, carbon dioxide, and soil organic matter by micro-organisms. In this study, 2-year experiment was conducted determine degradation properties...
Instruction tuning has emerged as a promising approach to enhancing large language models in following human instructions. It is shown that increasing the diversity and number of instructions training data can consistently enhance generalization performance, which facilitates recent endeavor collect various integrate existing instruction datasets into larger collections. However, different users have their unique ways expressing instructions, there often exist variations across styles...
Optical fiber thermometers offer several advantages over refractive optics thermometers. Besides eliminating the need for a direct line of sight to measured surface, it is special value use in high electric or magnetic fields, strong rf microwave fields due electrically nonconducting nature optical fibers. At present, fluorescent thermometer has been developed and used temperature measurement as low -200 degree(s)C, but its contact modality limits application surface moving objects. A...