Large language models (LLMs) have demonstrated remarkable capabilities across various professional domains, with their performance typically evaluated through standardized benchmarks. In the financial field, the stringent demands for professional accuracy and real-time data processing often necessitate the use of retrieval-augmented generation (RAG) techniques. However, the development of financial RAG benchmarks has been constrained by data confidentiality issues and the lack of dynamic data integration. To address this issue, we introduce FinS-Pilot, a novel benchmark for evaluating RAG systems in online financial applications. Constructed from real-world financial assistant interactions, our benchmark incorporates both real-time API data and text data, organized through an intent classification framework covering critical financial domains. The benchmark enables comprehensive evaluation of financial assistants' capabilities in handling both static knowledge and time-sensitive market information.Through systematic experiments with multiple Chinese leading LLMs, we demonstrate FinS-Pilot's effectiveness in identifying models suitable for financial applications while addressing the current gap in specialized evaluation tools for the financial domain. Our work contributes both a practical evaluation framework and a curated dataset to advance research in financial NLP systems. The code and dataset are accessible on GitHub.

Code is available at https://github.com/ivam-he/BernNet .

Digital Humanities (DH) is an interdisciplinary field that integrates computational methods with humanities scholarship to investigate innovative topics. Each academic discipline follows a unique developmental path shaped by the topics researchers investigate and the methods they employ. With the help of bibliometric analysis, most of previous studies have examined DH across multiple dimensions such as research hotspots, co-author networks, and institutional rankings. However, these studies have often been limited in their ability to provide deep insights into the current state of technological advancements and topic development in DH. As a result, their conclusions tend to remain superficial or lack interpretability in understanding how methods and topics interrelate in the field. To address this gap, this study introduced a new concept of Topic-Method Composition (TMC), which refers to a hybrid knowledge structure generated by the co-occurrence of specific research topics and the corresponding method. Especially by analyzing the interaction between TMCs, we can see more clearly the intersection and integration of digital technology and humanistic subjects in DH. Moreover, this study developed a TMC-based workflow combining bibliometric analysis, topic modeling, and network analysis to analyze the development characteristics and patterns of research disciplines. By applying this workflow to large-scale bibliometric data, it enables a detailed view of the knowledge structures, providing a tool adaptable to other fields.

Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic communities. Despite the proposal of many advanced memory models in recent research, however, there remains a lack of unified implementations under a general framework. To address this issue, we develop a unified and modular library for developing advanced memory models of LLM-based agents, called MemEngine. Based on our framework, we implement abundant memory models from recent research works. Additionally, our library facilitates convenient and extensible memory development, and offers user-friendly and pluggable memory usage. For benefiting our community, we have made our project publicly available at https://github.com/nuster1128/MemEngine.

Real-world event sequences are often generated by different temporal point processes (TPPs) and thus have clustering structures. Nonetheless, in the modeling and prediction of event sequences, most existing TPPs ignore the inherent clustering structures of the event sequences, leading to the models with unsatisfactory interpretability. In this study, we learn structure-enhanced TPPs with the help of Gromov-Wasserstein (GW) regularization, which imposes clustering structures on the sequence-level embeddings of the TPPs in the maximum likelihood estimation framework.In the training phase, the proposed method leverages a nonparametric TPP kernel to regularize the similarity matrix derived based on the sequence embeddings. In large-scale applications, we sample the kernel matrix and implement the regularization as a Gromov-Wasserstein (GW) discrepancy term, which achieves a trade-off between regularity and computational efficiency.The TPPs learned through this method result in clustered sequence embeddings and demonstrate competitive predictive and clustering performance, significantly improving the model interpretability without compromising prediction accuracy.

The ability of the foundation models heavily relies on large-scale, diverse, and high-quality pretraining data. In order to improve data quality, researchers and practitioners often have to manually curate datasets from difference sources and develop dedicated data cleansing pipeline for each data repository. Lacking a unified data processing framework, this process is repetitive and cumbersome. To mitigate this issue, we propose a data processing framework that integrates a Processing Module which consists of a series of operators at different granularity levels, and an Analyzing Module which supports probing and evaluation of the refined data. The proposed framework is easy to use and highly flexible. In this demo paper, we first introduce how to use this framework with some example use cases and then demonstrate its effectiveness in improving the data quality with an automated evaluation with ChatGPT and an end-to-end evaluation in pretraining the GPT-2 model. The code and demonstration videos are accessible on GitHub.

To facilitate the research on intelligent and human-like chatbots with multi-modal context, we introduce a new video-based multi-modal dialogue dataset, called TikTalk. We collect 38K videos from a popular video-sharing platform, along with 367K conversations posted by users beneath them. Users engage in spontaneous conversations based on their multi-modal experiences from watching videos, which helps recreate real-world chitchat context. Compared to previous multi-modal dialogue datasets, the richer context types in TikTalk lead to more diverse conversations, but also increase the difficulty in capturing human interests from intricate multi-modal information to generate personalized responses. Moreover, external knowledge is more frequently evoked in our dataset. These facts reveal new challenges for multi-modal dialogue models. We quantitatively demonstrate the characteristics of TikTalk, propose a video-based multi-modal chitchat task, and evaluate several dialogue baselines. Experimental results indicate that the models incorporating large language models (LLM) can generate more diverse responses, while the model utilizing knowledge graphs to introduce external knowledge performs the best overall. Furthermore, no existing model can solve all the above challenges well. There is still a large room for future improvements, even for LLM with visual extensions. Our dataset is available at \url{https://ruc-aimind.github.io/projects/TikTalk/}.

Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming. Despite the impressive capabilities of large language models like ChatGPT in generating programs by interacting with users through natural language prompts, there are still limitations. Specifically, a user must provide specific prompts to iteratively guide ChatGPT in improving data preparation programs, which requires a certain level of expertise in programming, the dataset used and the ML task. Moreover, once a program has been generated, it is non-trivial to revisit a previous version or make changes to the program without starting the process over again. In this paper, we present ChatPipe, a novel system designed to facilitate seamless interaction between users and ChatGPT. ChatPipe provides users with effective recommendation on next data preparation operations, and guides ChatGPT to generate program for the operations. Also, ChatPipe enables users to easily roll back to previous versions of the program, which facilitates more efficient experimentation and testing. We have developed a web application for ChatPipe and prepared several real-world ML tasks from Kaggle. These tasks can showcase the capabilities of ChatPipe and enable VLDB attendees to easily experiment with our novel features to rapidly orchestrate a high-quality data preparation program.

Huawei Technologies' Ascend chip, China's most powerful artificial intelligence (AI) processor, can outperform Nvidia's flagship V100 chip in certain tasks, but also has some serious shortcomings, according to a new study by Chinese scientists. The researchers evaluated the Ascend processor's performance in various applications to gain the first in-depth look at China's growing competence as well as weakness in AI chip technology. Despite not being fully aligned with international flagship chips in overall performance, researchers said the Huawei Ascend processor could be used across most existing applications, and in some scenarios even surpass the performance of global competitors. The evaluation, carried out by researchers at China's Renmin University and Tsinghua University, was published in the peer-reviewed Chinese Journal of Computers in August, just before Washington banned US sales of the most powerful AI chips to China. Graphics processing units (GPUs) were originally developed to render images in video games, but in the past decade they have been increasingly deployed in the largest supercomputers by scientists and internet companies.

We present an algorithm (LsNet2Vec) that, given a large-scale network (millions of nodes), embeds the structural features of node into a lower and fixed dimensions of vector in the set of real numbers. We experiment and evaluate our proposed approach with twelve datasets collected from SNAP. Results show that our model performs comparably with state-of-the-art methods, such as Katz method and Random Walk Restart method, in various experiment settings.