Search

Your search keyword '"Guo, Yue"' showing total 535 results
Start Over Author "Guo, Yue" Publication Year Range This year
535 results on '"Guo, Yue"'

2. Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models

Author

Lin, Muhan, Shi, Shuyang, Guo, Yue, Chalaki, Behdad, Tadiparthi, Vaishnav, Pari, Ehsan Moradi, Stepputtis, Simon, Campbell, Joseph, and Sycara, Katia

Subjects
Computer Science - Artificial Intelligence
Abstract

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning from human feedback is a successful technique that can mitigate such issues, however, the collection of human feedback can be laborious. Recent works have solicited feedback from pre-trained large language models rather than humans to reduce or eliminate human effort, however, these approaches yield poor performance in the presence of hallucination and other errors. This paper studies the advantages and limitations of reinforcement learning from large language model feedback and proposes a simple yet effective method for soliciting and applying feedback as a potential-based shaping function. We theoretically show that inconsistent rankings, which approximate ranking errors, lead to uninformative rewards with our approach. Our method empirically improves convergence speed and policy returns over commonly used baselines even with significant ranking errors, and eliminates the need for complex post-processing of reward functions., Comment: 13 pages, 8 figures, The 2024 Conference on Empirical Methods in Natural Language Processing

Published
2024

3. Optimally robust shortcuts to population inversion in cat-state qubits

Author

Xu, Shao-Wei, Zhang, Zhong-Zheng, Guo, Yue-Ying, Chen, Ye-Hong, and Xia, Yan

Subjects
Quantum Physics
Abstract

Cat-state qubits formed by photonic coherent states are a promising candidate for realizing fault-tolerant quantum computing. Such logic qubits have a biased noise channel that the bit-flip error dominates over all the other errors. In this manuscript, we propose an optimally robust protocol using the control method of shortcuts to adiabaticity to realize a nearly perfect population inversion in a cat-state qubit. We construct a shortcut based on the Lewis-Riesenfeld invariant and examine the stability versus different types of perturbations for the fast and robust population inversion. Numerical simulations demonstrate that the population inversion can be mostly insensitive to systematic errors in our protocol. Even when the parameter imperfection rate for bit-flip control is $20\%$, the final population of the target state can still reach $\geq 99\%$. The optimally robust control provides a feasible method for fault-tolerant and scalable quantum computation., Comment: 9 pages, 8 figures, comments are welcome

Published
2024

4. CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge

Author

Zheng, Tianshi, Bai, Jiaxin, Wang, Yicheng, Fang, Tianqing, Guo, Yue, Yim, Yauwai, and Song, Yangqiu

Subjects
Computer Science - Computation and Language
Abstract

While large language models (LLMs) have demonstrated impressive capabilities across various natural language processing tasks by acquiring rich factual knowledge from their broad training data, their ability to synthesize and logically reason with this knowledge in complex ways remains underexplored. In this work, we present a systematic evaluation of state-of-the-art LLMs' complex logical reasoning abilities through a novel benchmark of automatically generated complex reasoning questions over general domain and biomedical knowledge graphs. Our extensive experiments, employing diverse in-context learning techniques, reveal that LLMs excel at reasoning over general world knowledge but face significant challenges with specialized domain-specific knowledge. We find that prompting with explicit Chain-of-Thought demonstrations can substantially improve LLM performance on complex logical reasoning tasks with diverse logical operations. Interestingly, our controlled evaluations uncover an asymmetry where LLMs display proficiency at set union operations, but struggle considerably with set intersections - a key building block of logical reasoning. To foster further work, we will publicly release our evaluation benchmark and code., Comment: 9 pages

Published
2024

5. EconNLI: Evaluating Large Language Models on Economics Reasoning

Author

Guo, Yue and Yang, Yi

Subjects
Computer Science - Computation and Language
Abstract

Large Language Models (LLMs) are widely used for writing economic analysis reports or providing financial advice, but their ability to understand economic knowledge and reason about potential results of specific economic events lacks systematic evaluation. To address this gap, we propose a new dataset, natural language inference on economic events (EconNLI), to evaluate LLMs' knowledge and reasoning abilities in the economic domain. We evaluate LLMs on (1) their ability to correctly classify whether a premise event will cause a hypothesis event and (2) their ability to generate reasonable events resulting from a given premise. Our experiments reveal that LLMs are not sophisticated in economic reasoning and may generate wrong or hallucinated answers. Our study raises awareness of the limitations of using LLMs for critical decision-making involving economic reasoning and analysis. The dataset and codes are available at https://github.com/Irenehere/EconNLI., Comment: Findings of ACL 2024

Published
2024

6. Improving Weak-to-Strong Generalization with Reliability-Aware Alignment

Author

Guo, Yue and Yang, Yi

Subjects
Computer Science - Computation and Language
Abstract

Large language models (LLMs) are now rapidly advancing and surpassing human abilities on many natural language tasks. However, aligning these super-human LLMs with human knowledge remains challenging because the supervision signals from human annotators may be wrong. This issue, known as the "super-alignment" problem, requires enhancing weak-to-strong generalization, where a strong LLM must generalize from imperfect supervision provided by a weaker source. To address this issue, we propose an approach to improve weak-to-strong generalization by involving the reliability of weak supervision signals in the alignment process. In our method, we query the weak supervisor for multiple answers, estimate the answer reliability, and enhance the alignment process by filtering out uncertain data or re-weighting reliable data. Experiments on four datasets demonstrate that our methods effectively identify the quality of weak labels and significantly enhance weak-to-strong generalization. Our work presents effective techniques for error-robust model alignment, reducing error propagation from noisy supervision and enhancing the accuracy and reliability of LLMs. Codes are publicly available at http://github.com/Irenehere/ReliableAlignment.

Published
2024

20. Research on Integrated Energy System Economic Dispatch Method Based on Proximal Policy Optimization

Author

LIU Zhiliang, GUO Yue, SHA Shuming, LIU Zhen, and QIANG Yan

Subjects
integrated energy system, economic dispatch, reinforcement learning, proximal policy optimization, Chemical engineering, TP155-156, Materials of engineering and construction. Mechanics of materials, TA401-492, Technology
Abstract

Purposes The economic dispatch of Integrated Energy Systems (IES) is a key research topic of energy technology reform, inherently a complex Mixed-Integer Nonlinear Programming problem. Traditional optimization methods have high computational complexity and struggle to adapt to the source-load uncertainty in IES coupled with renewable energy systems. Utilizing Deep Reinforcement Learning to decompose and accelerate the original problem enhances the efficiency of the IES economic dispatch model. Methods To address these issues, in this paper, an IES optimization dispatch framework based on an improved Proximal Policy Optimization (PPO) algorithm is proposed. The PPO algorithm is used to approximate some variables of the nonlinear constraints in the original model, converting them into linear constraints to speed up the solution. Findings The effectiveness and efficiency of this method over others are validated through case studies, predicting significant computational advantages in large-scale IES optimization problems.

Published
2024
Full Text
View/download PDF

23. Preliminary Study of High Mach Arc Aerodynamic Test Wind Tunnel

Author

Zhang, Tingting, Lin, Jian, Qu, Zhenle, Guo, Yue, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, and Fu, Song, editor

Published
2024
Full Text
View/download PDF

24. Reliability Analysis of CTCS-3 Security Services Based on 5G-R Using Timed Colored Petri Nets

Author

Qiao, Wanqi, Sun, Bin, Guo, Yue, Ding, Jianwen, Wang, Wei, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Tan, Kay Chen, Series Editor, Yang, Jianwei, editor, Yao, Dechen, editor, Liu, Zhigang, editor, and Diao, Lijun, editor

Published
2024
Full Text
View/download PDF

25. Prognostic Value of Serum α‐Fetoprotein Level as an Important Characteristic of Tumor Biology for Patients Undergoing Liver Resection of Early-Stage Hepatocellular Carcinoma (BCLC Stage 0/A): A Large Multicenter Analysis

Author

Yao, Lan-Qing, Fan, Zhong-Qi, Wang, Ming-Da, Diao, Yong-Kang, Chen, Ting-Hao, Zeng, Yong-Yi, Chen, Zhong, Wang, Xian-Ming, Zhou, Ya-Hao, Li, Jie, Fan, Xin-Ping, Liang, Ying-Jian, Li, Chao, Shen, Feng, Lv, Guo-Yue, and Yang, Tian

Published
2024
Full Text
View/download PDF

38. Temporal variations in the short-term effects of ambient air pollution on cardiovascular and respiratory mortality: a pooled analysis of 380 urban areas over a 22-year period

Author

Kan, Haidong, Osorio, Samuel, Orru, Hans, Indermitte, Ene, Maasikmets, Marek, Ryti, Niilo, Pascal, Mathilde, Katsouyanni, Klea, Analitis, Antonis, Entezari, Alireza, Mayvaneh, Fatemeh, Kim, Yoonhee, Alahmad, Barrak, Hurtado Diaz, Magali, Félix Arellano, Eunice Elizabeth, Rao, Shilpa, Diz-Lois Palomares, Alfonso, Scovronick, Noah, Acquaotta, Fiorella, Kim, Ho, Lee, Whanhee, Íñiguez, Carmen, Forsberg, Bertil, Ragettli, Martina S, Guo, Yue Leon, Pan, Shih-Chun, Li, Shanshan, Zanobetti, Antonella, Schwarz, Maximilian, Peters, Annette, Stafoggia, Massimo, de'Donato, Francesca, Sera, Francesco, Bell, Michelle L, Guo, Yuming, Honda, Yasushi, Huber, Veronika, Jaakkola, Jouni J K, Urban, Aleš, Vicedo-Cabrera, Ana Maria, Masselot, Pierre, Lavigne, Eric, Achilleos, Souzana, Kyselý, Jan, Samoli, Evangelia, Hashizume, Masahiro, Fook Sheng Ng, Chris, das Neves Pereira da Silva, Susana, Madureira, Joana, Garland, Rebecca M, Tobias, Aurelio, Armstrong, Ben, Schwartz, Joel, Gasparrini, Antonio, Schneider, Alexandra, and Breitner, Susanne

Published
2024
Full Text
View/download PDF

39. Risks of infectious disease hospitalisations in the aftermath of tropical cyclones: a multi-country time-series study

Author

Huang, Wenzhong, Vogt, Thomas, Park, Jinah, Yang, Zhengyu, Ritchie, Elizabeth A, Xu, Rongbin, Zhang, Yiwen, Hales, Simon, Yu, Wenhua, Hundessa, Samuel, Otto, Christian, Yu, Pei, Liu, Yanming, Ju, Ke, Lavigne, Eric, Ye, Tingting, Wen, Bo, Wu, Yao, Kliengchuay, Wissanupong, Tantrakarnapa, Kraichat, Guo, Yue Leon, Kim, Ho, Phung, Dung, Li, Shanshan, and Guo, Yuming

Published
2024
Full Text
View/download PDF

42. Stratifying risk of failure to achieve textbook outcomes among patients undergoing hepatectomy for hepatocellular carcinoma: A multicenter score validation study

Author

Liu, Han, Diao, Yong-Kang, Wei, Feng, Wang, Si-Yuan, Liang, Ying-Jian, Wu, Yi-Fan, Zheng, Qi-Xuan, Wang, Xian-Ming, Wang, Hong, Li, Jie, Chen, Ting-Hao, Wu, Xiao-Chang, Gu, Wei-Min, Zhou, Ya-Hao, Guo, Hong-Wei, Shao, Guang-Zhao, Xu, Jia-Hao, Yao, Lan-Qing, Wang, Ming-Da, Shen, Feng, Pawlik, Timothy M., Lau, Wan Yee, Lv, Guo-Yue, and Yang, Tian

Published
2024
Full Text
View/download PDF

43. Identification of prognostic biomarkers for cholangiocarcinoma by combined analysis of molecular characteristics of clinical MVI subtypes and molecular subtypes

Author

Li, Ming-Yue, Liu, Ya-Hui, Wei, Feng, Zhang, Ping, Sun, Xiao-Dong, Wang, Meng, Du, Xiao-Hong, Ye, Jun-Feng, Qiu, Wei, Shi, Xiao-Ju, Ji, Bai, Wang, Ying-Chao, Jiang, Chao, Chai, Wen-Gang, Huang, Bo, Liu, Xing-Kai, Chen, Qing-Min, Fu, Yu, Hu, Xin-Tong, Chen, Li-Guo, He, Jia-Xue, Chai, Kai-Yuan, Gou, Zhao-Ming, Yang, Tian, Wang, Guang-Yi, Jiang, Yan-Fang, Fan, Zhong-Qi, and Lv, Guo-Yue

Published
2024
Full Text
View/download PDF

46. Reduced miR‐513a‐5p expression in COPD may regulate airway mucous cell hyperplasia through TFR1‐dependent signaling

Author

Jia Zhou, Jun‐Yi Du, Rui Xu, Xiao‐Juan Wu, and Guo‐Yue Zhang

Subjects
airway mucous cell hyperplasia, COPD, miR‐513a‐5p, transferrin receptor, Medicine (General), R5-920
Abstract

Abstract Airway mucous cell metaplasia and mucous hypersecretion is one of the key characteristic pathophysiological status of chronic obstructive pulmonary disease (COPD). micro(mi)RNAs are acknowledged as non‐encoding RNA molecules playing important roles in gene expression regulation. In this study, we searched the Gene Expression Omnibus (GEO) database for the differentially expressed miRNAs between COPD and non‐COPD controls with bioinformatics analysis. Finally, we focused on miR‐513a‐5p and investigated the potential mechanism by which miR‐513a‐5p regulates airway mucous hypersecretion and goblet cell metaplasia. A dual‐luciferase reporter assay was then showing that miR‐513a‐5p targeted the 3′‐UTR of TFR1 and inhibited its expression in vitro. In vivo transfection demonstrated that TFR1 downregulation partially blocked MUC5AC hypersecretion and goblet cell hyperplasia in COPD model rats. In vitro study, CSE increased the intracellular expression and secretion of MUC5AC by BEAS‐2B branchial epithelial cells in the BEAS‐2B cell and THP‐1 cell coculture system. Coculture with either miR‐513a‐5p mimic‐pretreated or TFR1‐deficient THP‐1 cells attenuated intracellular MUC5AC expression in BEAS‐2B cells exposed to CSE. ELISA demonstrated that transfection of TFR1 siRNA or pretreatment with miR‐513a‐5p mimic reduced the secretion of inflammatory factors that are responsible for airway goblet cell hyperplasia, such as IL‐1β, IL‐13, and IL‐17, by THP‐1 cells after CSE stimulation. Our findings supported that miR‐513a‐5p/TFR1 signaling axis might activate macrophages as well as promote airway inflammation and airway mucous cell hyperplasia in COPD.

Published
2024
Full Text
View/download PDF

47. Extreme Temperatures and Stroke Mortality: Evidence From a Multi-Country Analysis

Author

Alahmad, Barrak, Khraishah, Haitham, Kamineni, Meghana, Royé, Dominic, Papatheodorou, Stefania I., Vicedo-Cabrera, Ana Maria, Guo, Yuming, Lavigne, Eric, Armstrong, Ben, Sera, Francesco, Bernstein, Aaron S., Zanobetti, Antonella, Garshick, Eric, Schwartz, Joel, Bell, Michelle L., Al-Mulla, Fahd, Koutrakis, Petros, Gasparrini, Antonio, Achilleos, Souzana, Acquaotta, Fiorella, Pan, Shih-Chun, Sousa Zanotti Stagliorio Coelho, Micheline, Colistro, Valentina, Ngoc Dang, Tran, Van Dung, Do, De’ Donato, Francesca K., Entezari, Alireza, Leon Guo, Yue-Liang, Hashizume, Masahiro, Honda, Yasushi, Indermitte, Ene, Íñiguez, Carmen, Jaakkola, Jouni J.K., Kim, Ho, Lee, Whanhee, Li, Shanshan, Madureira, Joana, Mayvaneh, Fatemeh, Orru, Hans, Overcenco, Ala, Ragettli, Martina S., Ryti, Niilo R.I., Hilario Nascimento Saldiva, Paulo, Scovronick, Noah, Seposo, Xerxes, Pereira Silva, Susana, Stafoggia, Massimo, and Tobias, Aurelio

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results