Cognitive diagnosis, which assesses the learners' competence from learners' interaction logs, plays a vital role in education. It provides a crucial reference for gauging learners' proficiency levels and tailoring future learning activities accordingly. Researchers have proposed numerous cognitive diagnosis models to address this task. Despite their success, these models continue to face the ill-posed problem because of the information loss caused by under-expressive interaction function and incomplete observations. In this paper, we address these challenges by proposing a novel cognitive diagnosis model, DMC-CDM, based on the theoretical premise that cognitive states can be captured with minimal information loss by maximizing the mutual information between observed and potential observations. Specifically, DMC-CDM incorporates a semantic extractor to provide a comprehensive semantic understanding of learners' interaction logs, thereby enhancing current collaborative-based cognitive state representations. It then consolidates multi-perspective observations to capture precise cognitive states by maximizing mutual information between these observations. We conducted extensive experiments on three datasets, and the experimental results demonstrate that our proposed model is both effective and beneficial for downstream applications in education.

Cheng Cheng, Zhenya Huang, GuanHao Zhao, Yuxiang Guo, Xin Lin, Jinze Wu, Xin Li, Shijin Wang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost. While powerful models deliver better results, they come at a high cost, whereas smaller models are more cost-effective but less capable. To address this trade-off, we propose IRT-Router, a multi-LLM routing framework that efficiently routes user queries to the most suitable LLM. Inspired by Item Response Theory (IRT), a psychological measurement methodology, IRT-Router explicitly models the relationship between LLM capabilities and user query attributes. This not only enables accurate prediction of response performance but also provides interpretable insights, such as LLM abilities and query difficulty. Additionally, we design an online query warm-up technique based on semantic similarity, further enhancing the online generalization capability of IRT-Router. Extensive experiments on 20 LLMs and 12 datasets demonstrate that IRT-Router outperforms most baseline methods in terms of effectiveness and interpretability. Its superior performance in cold-start scenarios further confirms the reliability and practicality of IRT-Router in real-world applications. Code is available at https://github.com/Mercidaiha/IRT-Router.

Time series forecasting plays a pivotal role in various real-world applications and has attracted significant attention in recent decades. While recent methods have achieved remarkable accuracy by incorporating advanced inductive biases and training strategies, we observe that instance-level variations remain a significant challenge. These variations—stemming from distribution shifts, missing data, and long-tail patterns—often lead to suboptimal forecasts for specific instances, even when overall performance appears strong. To address this issue, we propose a model-agnostic framework, PIR, designed to enhance forecasting performance through Post-forecasting Identification and Revision. Specifically, PIR first identifies biased forecast instances by estimating their predictive accuracy. Based on this, the framework revises the forecasts using contextual information, including covariates and historical time series, from both local and global perspectives in a post-processing fashion. Extensive experiments on real-world datasets with mainstream forecasting models demonstrate that PIR effectively mitigates instance-level errors and significantly improves forecasting reliability.

An intelligent code search engine tries to find and suggest a code piece given a developer's query quickly from a large-scale program database, which can significantly promote software development efficiency. Existing solutions can search the relevant codes to some extent. However, most of them fail to precisely understand the search intent of developers since they only mine their natural language queries, while ignoring the valuable programming context (e.g., the code written by the developer). In this paper, we study the novel problem of context-aware code search. To promote a step forward, we first provide the CodeSearchNet-C dataset with constructing sufficient programming context from the GitHub website for each query-code instance. The dataset is supplemented on the CodeSearchNet benchmark, ensuring both generality and comparability for relevant research. Then, by analyzing the characteristics of programming context, we propose a novel two-stage Context-aware Code Retrieval (ConCR) framework. In the first stage, we propose a Context Walking algorithm, which simulates the programming habits of different developers. The generated programming context could ensure the diversity of search intent among developers. In the second stage, imitating the reading habits of developers, we introduce a novel Context Hierarchical Encoder, to understand the search intent with contextual information from local to global. Our ConCR framework is general, and we give three implementations on the basis of typical code search models as backbones. Extensive experimental results clearly prove that our ConCR significantly enhances the code search performance, effectively fulfilling developers' needs for efficient code resource searching on the web. These results also verify the necessity of introducing programming context to understand developers' intent.

The fundamental task of intelligent educational systems is to offer adaptive learning services to students, such as exercise recommendations and computerized adaptive testing. However, optimizing required models in these systems would always encounter the collection difficulty of high-quality interaction data in practice. Therefore, establishing a student simulator is of great value since it can generate valid interactions to help optimize models. Existing advances have achieved success but generally suffer from exposure bias and overlook long-term intentions. To tackle these problems, we propose a novel Direct-Adversarial Imitation Student Simulator (DAISim) by formulating it as a Markov Decision Process (MDP), which unifies the workflow of the simulator in training and generating to alleviate the exposure bias and single-step optimization problems. To construct the intentions underlying the complex student interactions, we first propose a direct imitation strategy to mimic the interactions with a simple reward function. Then, we propose an adversarial imitation strategy to learn a rational distribution with the reward given by a parameterized discriminator. Furthermore, we optimize the discriminator in adversarial imitation in a pairwise manner, and the theoretical analysis shows that the pairwise discriminator would improve the generation quality. We conduct extensive experiments on real-world datasets, where the results demonstrate that our DAISim can simulate high-quality student interactions whose distribution is close to real distribution and can promote several downstream services.

Computerized adaptive testing (CAT), as a tool that can efficiently measure student's ability, has been widely used in various standardized tests (e.g., GMAT and GRE). The adaptivity of CAT refers to the selection of the most informative questions for each student, reducing test length. Existing CAT methods do not explicitly target ability estimation accuracy since there is no student's true ability as ground truth; therefore, these methods cannot be guaranteed to make the estimate converge to the true with such limited responses. In this paper, we analyze the statistical properties of estimation and find a theoretical approximation of the true ability: the ability estimated by full responses to question bank. Based on this, a Bounded Ability Estimation framework for CAT (BECAT) is proposed in a data-summary manner, which selects a question subset that closely matches the gradient of the full responses. Thus, we develop an expected gradient difference approximation to design a simple greedy selection algorithm, and show the rigorous theoretical and error upper-bound guarantees of its ability estimate. Experiments on both real-world and synthetic datasets, show that it can reach the same estimation accuracy using 15\% less questions on average, significantly reducing test length.