Yanhong Bai

Yanhong Bai, Jiabao Zhao, Jinxin Shi et al.

Detecting stereotypes and biases in Large Language Models (LLMs) can enhance fairness and reduce adverse impacts on individuals or groups when these LLMs are applied. However, the majority of existing methods focus on measuring the model's preference towards sentences containing biases and stereotypes within datasets, which lacks interpretability and cannot detect implicit biases and stereotypes in the real world. To address this gap, this paper introduces a four-stage framework to directly evaluate stereotypes and biases in the generated content of LLMs, including direct inquiry testing, serial or adapted story testing, implicit association testing, and unknown situation testing. Additionally, the paper proposes multi-dimensional evaluation metrics and explainable zero-shot prompts for automated evaluation. Using the education sector as a case study, we constructed the Edu-FairMonitor based on the four-stage framework, which encompasses 12,632 open-ended questions covering nine sensitive factors and 26 educational scenarios. Experimental results reveal varying degrees of stereotypes and biases in five LLMs evaluated on Edu-FairMonitor. Moreover, the results of our proposed automated evaluation method have shown a high correlation with human annotations.

Shangheng Du, Jiabao Zhao, Jinxin Shi et al.

With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness or suboptimal performance in complex agent-related environments. Although LLM optimization techniques can improve model performance across many general tasks, they lack specialized optimization towards critical agent functionalities such as long-term planning, dynamic environmental interaction, and complex decision-making. Although numerous recent studies have explored various strategies to optimize LLM-based agents for complex agent tasks, a systematic review summarizing and comparing these methods from a holistic perspective is still lacking. In this survey, we provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods. We first focus on parameter-driven optimization, covering fine-tuning-based optimization, reinforcement learning-based optimization, and hybrid strategies, analyzing key aspects such as trajectory data construction, fine-tuning techniques, reward function design, and optimization algorithms. Additionally, we briefly discuss parameter-free strategies that optimize agent behavior through prompt engineering and external knowledge retrieval. Finally, we summarize the datasets and benchmarks used for evaluation and tuning, review key applications of LLM-based agents, and discuss major challenges and promising future directions. Our repository for related references is available at https://github.com/YoungDubbyDu/LLM-Agent-Optimization.

Yanhong Bai, Yongke Wu, Xiaoping Xie

Superconvergence and a posteriori error estimators of recovery type are analyzed for the 4-node hybrid stress quadrilateral finite element method proposed by Pian and Sumihara (Int. J. Numer. Meth. Engrg., 1984, 20: 1685-1695) for linear elasticity problems. Uniform superconvergence of order $O(h^{1+\min\{α,1\}})$ with respect to the Lamé constant $λ$ is established for both the recovered gradients of the displacement vector and the stress tensor under a mesh assumption, where $α>0$ is a parameter characterizing the distortion of meshes from parallelograms to quadrilaterals. A posteriori error estimators based on the recovered quantities are shown to be asymptotically exact. Numerical experiments confirm the theoretical results.

Yanhong Bai, Jiabao Zhao, Tingjiang Wei et al.

With the long term accumulation of high quality educational data, artificial intelligence has shown excellent performance in knowledge tracing. However, due to the lack of interpretability and transparency of some algorithms, this approach will result in reduced stakeholder trust and a decreased acceptance of intelligent decisions. Therefore, algorithms need to achieve high accuracy, and users need to understand the internal operating mechanism and provide reliable explanations for decisions. This paper thoroughly analyzes the interpretability of KT algorithms. First, the concepts and common methods of explainable artificial intelligence and knowledge tracing are introduced. Next, explainable knowledge tracing models are classified into two categories: transparent models and black box models. Then, the interpretable methods used are reviewed from three stages: ante hoc interpretable methods, post hoc interpretable methods, and other dimensions. It is worth noting that current evaluation methods for explainable knowledge tracing are lacking. Hence, contrast and deletion experiments are conducted to explain the prediction results of the deep knowledge tracing model on the ASSISTment2009 by using three XAI methods. Moreover, this paper offers some insights into evaluation methods from the perspective of educational stakeholders. This paper provides a detailed and comprehensive review of the research on explainable knowledge tracing, aiming to offer some basis and inspiration for researchers interested in the interpretability of knowledge tracing.

Qizhi Zheng, Ayang Zhao, Xinzhu Wang et al.

Participants: This study employed a combination of Vector Autoregression (VAR) model and Graph Neural Networks (GNN) to systematically construct dynamic causal inference. Multiple classic classification algorithms were compared, including Random Forest, Logistic Regression, XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Gradient Boosting, and Multi Layer Perceptron (MLP). The SMOTE algorithm was used to undersample a small number of samples and employed Stratified K-fold Cross Validation. Results: This study included a total of 11,789 participants, including 6,334 females (53.73%) and 5,455 males (46.27%), with an average age of 65 years. Introduction of dynamic causal inference features has significantly improved the performance of almost all models. The area under the ROC curve of each model ranged from 0.78 to 0.83, indicating significant difference (P < 0.01). Among all the models, the Gradient Boosting model demonstrated the highest performance and stability. Model explanation and feature importance analysis generated model interpretation that illustrated significant contributors associated with risks of stroke. Conclusions and Relevance: This study proposes a stroke risk prediction method that combines dynamic causal inference with machine learning models, significantly improving prediction accuracy and revealing key health factors that affect stroke. The research results indicate that dynamic causal inference features have important value in predicting stroke risk, especially in capturing the impact of changes in health status over time on stroke risk. By further optimizing the model and introducing more variables, this study provides theoretical basis and practical guidance for future stroke prevention and intervention strategies.

Yanhong Bai, Jiabao Zhao, Jinxin Shi et al.

Detecting stereotypes and biases in Large Language Models (LLMs) is crucial for enhancing fairness and reducing adverse impacts on individuals or groups when these models are applied. Traditional methods, which rely on embedding spaces or are based on probability metrics, fall short in revealing the nuanced and implicit biases present in various contexts. To address this challenge, we propose the FairMonitor framework and adopt a static-dynamic detection method for a comprehensive evaluation of stereotypes and biases in LLMs. The static component consists of a direct inquiry test, an implicit association test, and an unknown situation test, including 10,262 open-ended questions with 9 sensitive factors and 26 educational scenarios. And it is effective for evaluating both explicit and implicit biases. Moreover, we utilize the multi-agent system to construst the dynamic scenarios for detecting subtle biases in more complex and realistic setting. This component detects the biases based on the interaction behaviors of LLMs across 600 varied educational scenarios. The experimental results show that the cooperation of static and dynamic methods can detect more stereotypes and biased in LLMs.