Chaolu Meng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Chaolu Meng has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Yongbo Bu
College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, China; Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry
3 shared publicationsYue Pei
Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China; University of Chinese Academy of Sciences, Beijing 100049, China
3 shared publicationsQing Liu
Department of Pain, The Affiliated Traditional Chinese Medicine Hospital of Southwest Medical University, Luzhou, 646000, Sichuan, China
2 shared publicationsQuan Zou
The Affiliated Hospital of Southwest Medical University
2 shared publications- Quan Zou
University of Electronic Science and Technology of China
2 shared publications Qun Li
Department of Pain, The Affiliated Traditional Chinese Medicine Hospital of Southwest Medical University, Luzhou, 646000, Sichuan, China
2 shared publications
Latest Publications
- Open Access
- 6 September 2026
- Published by Elsevier in SSRN Electronic Journal
An AI4Research Scoring Benchmark: Characterizing and Calibrating LLM Evaluation of Automated Research Protocols
Automated research (AI4Research) increasingly delegates both generation and evaluation of scientific content to large language models (LLMs). Evaluation of AI-generated experimental protocols still relies on LLM-as-judge scoring, whose systematic inflation threatens the reliability of research automation. To characterize this problem, we construct a benchmark that stress-tests three families of mainstream LLM usage: fifteen agent reasoning frameworks, five reinforcement-learning strategies (PPO, GRPO, GSPO, DAPO, and ODP), and retrieval-augmented generation with dense, sparse, and hybrid retrieval. We contribute a methodology-centric dataset of 4,946 peer-reviewed machine-learning papers annotated through a six-stage progressive scheme with Long Chain-of-Thought formatting, and fine-tune 14 representative LLMs as generators. We further test the benchmark on biomedical research problems, a knowledge-intensive non-ML domain, and find that score inflation is amplified precisely where factual grounding is weakest. Across all settings we characterize five manifestations of score inflation, including self-evaluation bias and score-quality decoupling. Grounded in these findings, we propose a staged protocol-generation framework combining persistent memory files, stepwise generation, and dual-judge plus human-expert cross-validation. This framework reduces the mean deviation between LLM-judge and human-expert scores to 10.3 points, less than half the 21 to 26 point deviation of every other approach, yielding protocols that approach expert judgment.
- 6 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAn AI4Research Scoring Benchmark: Characterizing and Calibrating LLM Evaluation of Automated Research Protocols
Automated research (AI4Research) increasingly delegates both generation and evaluation of scientific content to large language models (LLMs). Evaluation of AI-generated experimental protocols still relies on LLM-as-judge scoring, whose systematic inflation threatens the reliability of research automation. To characterize this problem, we construct a benchmark that stress-tests three families of mainstream LLM usage: fifteen agent reasoning frameworks, five reinforcement-learning strategies (PPO, GRPO, GSPO, DAPO, and ODP), and retrieval-augmented generation with dense, sparse, and hybrid retrieval. We contribute a methodology-centric dataset of 4,946 peer-reviewed machine-learning papers annotated through a six-stage progressive scheme with Long Chain-of-Thought formatting, and fine-tune 14 representative LLMs as generators. We further test the benchmark on biomedical research problems, a knowledge-intensive non-ML domain, and find that score inflation is amplified precisely where factual grounding is weakest. Across all settings we characterize five manifestations of score inflation, including self-evaluation bias and score-quality decoupling. Grounded in these findings, we propose a staged protocol-generation framework combining persistent memory files, stepwise generation, and dual-judge plus human-expert cross-validation. This framework reduces the mean deviation between LLM-judge and human-expert scores to 10.3 points, less than half the 21 to 26 point deviation of every other approach, yielding protocols that approach expert judgment.
- 8 August 2024
- Published by Elsevier in Journal of Molecular Biology
- Vol. 437 (6) , 168741
IIFS2.0: An Improved Incremental Feature Selection Method for Protein Sequence Processing Based on a Caching Strategy
- 8 August 2024
- Published by Elsevier in Journal of Molecular Biology
- Vol. 437 (6) , 168741
IIFS2.0: An Improved Incremental Feature Selection Method for Protein Sequence Processing Based on a Caching Strategy
- Open Access
- 14 April 2024
- Published by Wiley
IIFS2.0: An Improved Incremental Feature Selection Method for Protein Sequence Processing Based on a Caching Strategy
The purpose of feature selection in protein sequence recognition problems is to select the optimal feature set and use it as training input for classifiers and discover key sequence features of specific proteins. In the feature selection process, relevant features associated with the target task will be retained, and irrelevant and redundant features will be removed. Therefore, in an ideal state, a feature combination with smaller feature dimensions and higher performance indicators is desired. This paper proposes an algorithm called IIFS2.0 based on the cache elimination strategy, which takes the local optimal combination of cached feature subsets as a breakthrough point. It searches for a new feature combination method through the cache elimination strategy to avoid the drawbacks of human factors and excessive reliance on feature sorting results. We validated and analyzed its effectiveness on the protein dataset, demonstrating that IIFS2.0 significantly reduces the dimensionality of feature combinations while also improving various evaluation indicators. In addition, we provide IIFS2.0 on http://112.124.26.17:8006/ for researchers to use.
- 14 April 2024
- Published by Wiley
Open AccessIIFS2.0: An Improved Incremental Feature Selection Method for Protein Sequence Processing Based on a Caching Strategy
The purpose of feature selection in protein sequence recognition problems is to select the optimal feature set and use it as training input for classifiers and discover key sequence features of specific proteins. In the feature selection process, relevant features associated with the target task will be retained, and irrelevant and redundant features will be removed. Therefore, in an ideal state, a feature combination with smaller feature dimensions and higher performance indicators is desired. This paper proposes an algorithm called IIFS2.0 based on the cache elimination strategy, which takes the local optimal combination of cached feature subsets as a breakthrough point. It searches for a new feature combination method through the cache elimination strategy to avoid the drawbacks of human factors and excessive reliance on feature sorting results. We validated and analyzed its effectiveness on the protein dataset, demonstrating that IIFS2.0 significantly reduces the dimensionality of feature combinations while also improving various evaluation indicators. In addition, we provide IIFS2.0 on http://112.124.26.17:8006/ for researchers to use.
- 25 October 2023
- Published by Wiley in Journal of Cellular Biochemistry
- Vol. 124 (11) , 1825-1834
Machine learning‐based antioxidant protein identification model: Progress and evaluation
Efficient and accurate identification of antioxidant proteins is of great significance. In recent years, many models for identifying antioxidant proteins have been proposed, but the low sensitivity and high dimensionality of the models are common problems. The generalization ability of the model needs to be improved. Researchers have tried different feature extraction algorithms and feature selection algorithms to obtain the most effective feature combination and have chosen more appropriate classification algorithms and tools to improve model performance. In this article, we systematically reviewed the data set of the most frequently used antioxidant proteins and the method selection for each step of model establishment and discussed the characteristics of each method. We have conducted a detailed analysis of recent research and believe that the practical ability and efficiency of model application can be improved by reducing model dimensions. The key to improving the performance of antioxidant protein recognition models in the future may lie in feature selection, so this paper also focuses on the combination of feature extraction and selection steps in the analysis of the model building process.
- 25 October 2023
- Published by Wiley in Journal of Cellular Biochemistry
- Vol. 124 (11) , 1825-1834
Machine learning‐based antioxidant protein identification model: Progress and evaluation
Efficient and accurate identification of antioxidant proteins is of great significance. In recent years, many models for identifying antioxidant proteins have been proposed, but the low sensitivity and high dimensionality of the models are common problems. The generalization ability of the model needs to be improved. Researchers have tried different feature extraction algorithms and feature selection algorithms to obtain the most effective feature combination and have chosen more appropriate classification algorithms and tools to improve model performance. In this article, we systematically reviewed the data set of the most frequently used antioxidant proteins and the method selection for each step of model establishment and discussed the characteristics of each method. We have conducted a detailed analysis of recent research and believe that the practical ability and efficiency of model application can be improved by reducing model dimensions. The key to improving the performance of antioxidant protein recognition models in the future may lie in feature selection, so this paper also focuses on the combination of feature extraction and selection steps in the analysis of the model building process.
- 23 February 2022
- Published by Elsevier in Analytical Biochemistry
- Vol. 645, 114625
TMPpred: A support vector machine-based thermophilic protein identifier
- 23 February 2022
- Published by Elsevier in Analytical Biochemistry
- Vol. 645, 114625
TMPpred: A support vector machine-based thermophilic protein identifier
- 26 July 2019
- Published by Wiley in Proteomics
- Vol. 19 (17) , 1900007
SecProMTB: Support Vector Machine‐Based Classifier for Secretory Proteins Using Imbalanced Data Sets Applied to Mycobacterium tuberculosis
Secretory proteins of Mycobacterium tuberculosis have created more concern, given their dominant immunogenicity and role in pathogenesis. In view of expensive and time‐consuming traditional biochemical experiments, an advanced support vector machine model named SecProMTB is constructed in this study and the proteins are identified by a bioinformatic approach. First, an improved pseudo‐amino acid composition (PseAAC) algorithm is used to extract features from all entities. Second, a novel imbalanced‐data strategy is proposed and adopted to divide the original data set into train set and test set. Third, to overcome the overfitting problem, feature‐ranking algorithms are applied with an increment feature selection. Finally, the model is trained and optimized. Consequently, a model is obtained with an area under the curve of 0.862 and average accuracy of 86% in the independent test. For the convenience of users, SecProMTB and related data are openly accessible at http://server.malab.cn/SecProMTB/index.jsp.
- 26 July 2019
- Published by Wiley in Proteomics
- Vol. 19 (17) , 1900007
SecProMTB: Support Vector Machine‐Based Classifier for Secretory Proteins Using Imbalanced Data Sets Applied to Mycobacterium tuberculosis
Secretory proteins of Mycobacterium tuberculosis have created more concern, given their dominant immunogenicity and role in pathogenesis. In view of expensive and time‐consuming traditional biochemical experiments, an advanced support vector machine model named SecProMTB is constructed in this study and the proteins are identified by a bioinformatic approach. First, an improved pseudo‐amino acid composition (PseAAC) algorithm is used to extract features from all entities. Second, a novel imbalanced‐data strategy is proposed and adopted to divide the original data set into train set and test set. Third, to overcome the overfitting problem, feature‐ranking algorithms are applied with an increment feature selection. Finally, the model is trained and optimized. Consequently, a model is obtained with an area under the curve of 0.862 and average accuracy of 86% in the independent test. For the convenience of users, SecProMTB and related data are openly accessible at http://server.malab.cn/SecProMTB/index.jsp.