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.

Wenzheng Zhang, Bingzheng Liu, Yang Hu et al.

Quantization-Aware Training from scratch has emerged as a promising approach for building efficient large language models (LLMs) with extremely low-bit weights (sub 2-bit), which can offer substantial advantages for edge deployment. However, existing methods still fail to achieve satisfactory accuracy and scalability. In this work, we identify a parameter democratization effect as a key bottleneck: the sensitivity of all parameters becomes homogenized, severely limiting expressivity. To address this, we propose pQuant, a method that decouples parameters by splitting linear layers into two specialized branches: a dominant 1-bit branch for efficient computation and a compact high-precision branch dedicated to preserving the most sensitive parameters. Through tailored feature scaling, we explicitly guide the model to allocate sensitive parameters to the high-precision branch. Furthermore, we extend this branch into multiple, sparsely-activated experts, enabling efficient capacity scaling. Extensive experiments indicate our pQuant achieves state-of-the-art performance in extremely low-bit quantization.

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).

Mingtao Zhang, Guoli Yang, Zhanxing Zhu et al.

Attention mechanisms have been extensively employed in various applications, including time series modeling, owing to their capacity to capture intricate dependencies; however, their utility is often constrained by quadratic computational complexity, which impedes scalability for long sequences. In this work, we propose a novel linear attention mechanism designed to overcome these limitations. Our approach is grounded in a theoretical demonstration that entropy, as a strictly concave function on the probability simplex, implies that distributions with aligned probability rankings and similar entropy values exhibit structural resemblance. Building on this insight, we develop an efficient approximation algorithm that computes the entropy of dot-product-derived distributions with only linear complexity, enabling the implementation of a linear attention mechanism based on entropy equality. Through rigorous analysis, we reveal that the effectiveness of attention in spatio-temporal time series modeling may not primarily stem from the non-linearity of softmax but rather from the attainment of a moderate and well-balanced weight distribution. Extensive experiments on four spatio-temporal datasets validate our method, demonstrating competitive or superior forecasting performance while achieving substantial reductions in both memory usage and computational time.

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.

Zhengwei Tao, Zhi Jin, Bincheng Li et al.

Predicting future events stands as one of the ultimate aspirations of artificial intelligence. Recent advances in large language model (LLM)-based systems have shown remarkable potential in forecasting future events, thereby garnering significant interest in the research community. Currently, several benchmarks have been established to evaluate the forecasting capabilities by formalizing the event prediction as a retrieval-augmented generation (RAG) and reasoning task. In these benchmarks, each prediction question is answered with relevant retrieved news articles. However, because there is no consideration on whether the questions can be supported by valid or sufficient supporting rationales, some of the questions in these benchmarks may be inherently noninferable. To address this issue, we introduce a new benchmark, PROPHET, which comprises inferable forecasting questions paired with relevant news for retrieval. To ensure the inferability of the benchmark, we propose Causal Intervened Likelihood (CIL), a statistical measure that assesses inferability through causal inference. In constructing this benchmark, we first collected recent trend forecasting questions and then filtered the data using CIL, resulting in an inferable benchmark for event prediction. Through extensive experiments, we first demonstrate the validity of CIL and in-depth investigations into event prediction with the aid of CIL. Subsequently, we evaluate several representative prediction systems on PROPHET, drawing valuable insights for future directions.

Fang Wang, Tianwei Yan, Zonghao Yang et al.

Multimodal Entity Linking (MEL) aims to associate textual and visual mentions with entities in a multimodal knowledge graph. Despite its importance, current methods face challenges such as incomplete contextual information, coarse cross-modal fusion, and the difficulty of jointly large language models (LLMs) and large visual models (LVMs). To address these issues, we propose DeepMEL, a novel framework based on multi-agent collaborative reasoning, which achieves efficient alignment and disambiguation of textual and visual modalities through a role-specialized division strategy. DeepMEL integrates four specialized agents, namely Modal-Fuser, Candidate-Adapter, Entity-Clozer and Role-Orchestrator, to complete end-to-end cross-modal linking through specialized roles and dynamic coordination. DeepMEL adopts a dual-modal alignment path, and combines the fine-grained text semantics generated by the LLM with the structured image representation extracted by the LVM, significantly narrowing the modal gap. We design an adaptive iteration strategy, combines tool-based retrieval and semantic reasoning capabilities to dynamically optimize the candidate set and balance recall and precision. DeepMEL also unifies MEL tasks into a structured cloze prompt to reduce parsing complexity and enhance semantic comprehension. Extensive experiments on five public benchmark datasets demonstrate that DeepMEL achieves state-of-the-art performance, improving ACC by 1%-57%. Ablation studies verify the effectiveness of all modules.

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.

Ming Wang, Fang Wang, Minghao Hu et al.

Long-form article generation (LFAG) presents challenges such as maintaining logical consistency, comprehensive topic coverage, and narrative coherence across extended articles. Existing datasets often lack both the hierarchical structure and fine-grained annotation needed to effectively decompose tasks, resulting in shallow, disorganized article generation. To address these limitations, we introduce DeFine, a Decomposed and Fine-grained annotated dataset for long-form article generation. DeFine is characterized by its hierarchical decomposition strategy and the integration of domain-specific knowledge with multi-level annotations, ensuring granular control and enhanced depth in article generation. To construct the dataset, a multi-agent collaborative pipeline is proposed, which systematically segments the generation process into four parts: Data Miner, Cite Retreiver, Q&A Annotator and Data Cleaner. To validate the effectiveness of DeFine, we designed and tested three LFAG baselines: the web retrieval, the local retrieval, and the grounded reference. We fine-tuned the Qwen2-7b-Instruct model using the DeFine training dataset. The experimental results showed significant improvements in text quality, specifically in topic coverage, depth of information, and content fidelity. Our dataset publicly available to facilitate future research.

Zhengwei Tao, Zhi Jin, Xiaoying Bai et al.

Events serve as fundamental units of occurrence within various contexts. The processing of event semantics in textual information forms the basis of numerous natural language processing (NLP) applications. Recent studies have begun leveraging large language models (LLMs) to address event semantic processing. However, the extent that LLMs can effectively tackle these challenges remains uncertain. Furthermore, the lack of a comprehensive evaluation framework for event semantic processing poses a significant challenge in evaluating these capabilities. In this paper, we propose an overarching framework for event semantic processing, encompassing understanding, reasoning, and prediction, along with their fine-grained aspects. To comprehensively evaluate the event semantic processing abilities of models, we introduce a novel benchmark called EVEVAL. We collect 8 datasets that cover all aspects of event semantic processing. Extensive experiments are conducted on EVEVAL, leading to several noteworthy findings based on the obtained results.