Zhenwen Liang

Zhenwen Liang

Auto-generated profile, based on publicly available information

Zhenwen Liang

University of Notre Dame, Notre Dame, Indiana, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 October 2020 in Green Chemistry
Verified
Journal Article
Open access
PDF file
RHRifan Hardian
Rifan Hardian
ZLZhenwen Liang
Zhenwen Liang
XZXiangliang Zhang
Xiangliang Zhang
G SG S
G S
Artificial intelligence in combination with design of experiments for sustainable process development achieving high quality metal–organic frameworks (MOFs) with minimal environmental effect.

21 October 2024
Verified
Conference Paper
Open access
QZQingkai Zeng
Qingkai Zeng
YBYuyang Bai
Yuyang Bai
ZTZhaoxuan Tan
Zhaoxuan Tan
SFShangbin Feng
Shangbin Feng
ZLZhenwen Liang
Zhenwen Liang
MJMeng Jiang
Meng Jiang
Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering. Manual curation of taxonomies is expensive in terms of human effort, making automatic taxonomy construction highly desirable. In this work, we introduce Chain-of-Layer which is an in-context learning framework designed to induct taxonomies from a given set of entities. Chain-of-Layer breaks down the task into selecting relevant candidate entities in each layer and gradually building the taxonomy from top to bottom. To minimize errors, we introduce the Ensemble-based Ranking Filter to reduce the hallucinated content generated at each iteration. Through extensive experiments, we demonstrate that Chain-of-Layer achieves state-of-the-art performance on four real-world benchmarks. Source code available at: https://github.com/qingkaizeng/chain-of-layer.


25 July 2023 in Highlights in Science, Engineering and Technology
Verified
Journal Article
Open access
Zehao LiZehao Li
Zehao Li
NLNianxu Lin
Nianxu Lin
RZRuibin Zou
Ruibin Zou
ZLZhenwen Liang
Zhenwen Liang
This paper mainly studies the important role of the percentage prediction of the number of users and the number of word-filling attempts of Wordle game in the future development strategy. The purpose of this article is to research and develop two mathematical models of Wordle game, one of which is the prediction model of user volume and the other is the percentage prediction model of the number of word-filling attempts. The fitting effect is very good, and the result is R2=0.984. By quantifying specific letters at different positions in a word, it is found that the proportion of difficult modes has a direct impact on specific positions and specific letters. Secondly, for the second model, the proportion of each corresponding variable is obtained through comprehensive evaluation and analysis by using the mean expectation model for the percentage of the predicted number of attempts. The average variance formula is used by calculating the average of the relevant percentage of each characteristic value under the corresponding number of attempts. The relevant percentage distribution results of "EERIE" (1, 2, 3, 4, 5, 6, X) are (1.20%, 16.01%, 28.31%, 27.83%, 18.16%, 5.81%). Through the analysis of variance, the P value is less than 0.05, and the prediction result of the model has high confidence.