Xiaoying Bai

Haiyang Shen, Jiuzheng Wang, Taian Guo et al.

As AI becomes part of everyday learning, many courses teach students to use it mainly as a productivity tool: how to prompt, search, summarize, write, code, and use tools more efficiently. We argue that AI education also needs a setting in which students learn to test AI and understand their own role in judging machine-produced knowledge. To this end, we introduce a course-based practice that teaches AI through benchmark construction, using deep research systems as a concrete example of AI-era knowledge work. Students turn disciplinary knowledge into verifiable expert-level questions, review one another's designs for ambiguity and shortcuts, and evaluate AI systems on the resulting tasks. This activity gives students direct exposure to a powerful tool while asking them to specify what a trustworthy answer would require. The produced benchmark, QuestBench, consists of 256 questions across 14 humanities and social-science domains. Evaluation on QuestBench shows that student-designed tasks reveal hidden failures in current deep research systems: across thirteen evaluated systems, the mean question-level pass rate is only 16.85%, and the best-performing system, GPT-5.5, reaches a 57.58% pass rate. The failures are educationally useful because they show how fluent, source-backed answers can still miss the right query, source, term, or evidence standard. Reflections from five student contributors suggest that benchmark construction can help students see professional knowledge not only as content AI may retrieve, but as the basis for judging AI outputs. We present QuestBench as a benchmark artifact and as a reusable classroom setting for a larger educational question: how students can remain responsible knowledge actors as AI enters learning and professional work. The dataset is available at https://huggingface.co/datasets/PKUAIWeb/QuestBench/tree/main.

Zhengwei Tao, Zhi Jin, Junqiang Huang et al.

Multi-modal Event Reasoning (MMER) endeavors to endow machines with the ability to comprehend intricate event relations across diverse data modalities. MMER is fundamental and underlies a wide broad of applications. Despite extensive instruction fine-tuning, current multi-modal large language models still fall short in such ability. The disparity stems from that existing models are insufficient to capture underlying principles governing event evolution in various scenarios. In this paper, we introduce Multi-Modal Event Evolution Learning (MEEL) to enable the model to grasp the event evolution mechanism, yielding advanced MMER ability. Specifically, we commence with the design of event diversification to gather seed events from a rich spectrum of scenarios. Subsequently, we employ ChatGPT to generate evolving graphs for these seed events. We propose an instruction encapsulation process that formulates the evolving graphs into instruction-tuning data, aligning the comprehension of event reasoning to humans. Finally, we observe that models trained in this way are still struggling to fully comprehend event evolution. In such a case, we propose the guiding discrimination strategy, in which models are trained to discriminate the improper evolution direction. We collect and curate a benchmark M-EV2 for MMER. Extensive experiments on M-EV2 validate the effectiveness of our approach, showcasing competitive performance in open-source multi-modal LLMs.

Mingjie Li, Xiaoying Bai, Minghua Ma et al.

Continuous Integration (CI) and Continuous Deployment (CD) are widely adopted in software engineering practice. In reality, the CI/CD pipeline execution is not yet reliably continuous because it is often interrupted by Docker build failures. However, the existing trial-and-error practice to detect faults is time-consuming. To timely detect Dockerfile faults, we propose a context-based pre-build analysis approach, named DockerMock, through mocking the execution of common Dockerfile instructions. A Dockerfile fault is declared when an instruction conflicts with the approximated and accumulated running context. By explicitly keeping track of whether the context is fuzzy, DockerMock strikes a good balance of detection precision and recall. We evaluated DockerMock with 53 faults in 41 Dockerfiles from open source projects on GitHub and 130 faults in 105 Dockerfiles from student course projects. On average, DockerMock detected 68.0% Dockerfile faults in these two datasets. While baseline hadolint detected 6.5%, and baseline BuildKit detected 60.5% without instruction execution. In the GitHub dataset, DockerMock reduces the number of builds to 47, outperforming that of hadolint (73) and BuildKit (74).

Zhengwei Tao, Xiancai Chen, Zhi Jin et al.

Events refer to specific occurrences, incidents, or happenings that take place under a particular background. Event reasoning aims to infer events according to certain relations and predict future events. The cutting-edge techniques for event reasoning play a crucial role in various natural language processing applications. Large language models (LLMs) have made significant advancements in event reasoning owing to their wealth of knowledge and reasoning capabilities. However, smaller instruction-tuned models currently in use do not consistently demonstrate exceptional proficiency in managing these tasks. This discrepancy arises from the absence of explicit modeling of events and the interconnections of them within their instruction data. Consequently, these models face challenges in comprehending event structures and semantics while struggling to bridge the gap between their interpretations and human understanding of events. Additionally, their limitations in grasping event relations lead to constrained event reasoning abilities to effectively deduce and incorporate pertinent event knowledge. In this paper, we propose Event-Oriented Instruction Tuning (EvIT) to train our LLM. Specifically, we first propose a novel structure named event quadruple which contains the structure and semantics of events and is complete in the event representation. We then design event-relation learning based on the structures. We encapsulate the learning into the instruction-tuning formulation to better stimulate the event reasoning capacity of our model. We design a heuristic unsupervised method to mine event quadruple from a large-scale corpus. At last, we finetune a Llama model on our Event-Oriented Instruction Tuning. We conduct extensive experiments on event reasoning tasks on several datasets. Automatic and human evaluations demonstrate EvIT achieves competitive performances on event reasoning.

Yilin Geng, Shujing Wang, Chuan Wang et al.

The Semantic Table Annotation (STA) task, which includes Column Type Annotation (CTA) and Cell Entity Annotation (CEA), maps table contents to ontology entities and plays important roles in various semantic applications. However, complex tables often pose challenges such as semantic loss of column names or cell values, strict ontological hierarchy requirements, homonyms, spelling errors, and abbreviations, which hinder annotation accuracy. To address these issues, this paper proposes an LLM-based agent approach for CTA and CEA. We design and implement five external tools with tailored prompts based on the ReAct framework, enabling the STA agent to dynamically select suitable annotation strategies depending on table characteristics. Experiments are conducted on the Tough Tables and BiodivTab datasets from the SemTab challenge, which contain the aforementioned challenges. Our method outperforms existing approaches across various metrics. Furthermore, by leveraging Levenshtein distance to reduce redundant annotations, we achieve a 70% reduction in time costs and a 60% reduction in LLM token usage, providing an efficient and cost-effective solution for STA.