The trading volume of China's secondary bond market reached CNY 2,735.44 trillion in 2024. The majority of transactions were conducted through the over-the-counter (OTC) market. In this market, brokers, buyers, and sellers send request-for-quote (RFQ) messages via group or private chats, generating an RFQ pool containing tens of thousands of requests. Brokers search through this pool to match suitable counterparties and facilitate transactions between them. The faster they match, the more trading opportunities and profits they can obtain. However, as RFQs are unstructured text messages, manual matching is time-consuming. Therefore, we built a system to accelerate this process. The core task of this system is to automatically parse RFQs into structured data, which faces two key challenges: highly domain-specific jargon in RFQs and the rapid evolution of jargon patterns. To address these challenges, we propose an RFQ parsing method based on fine-tuned large language models (LLMs). It consists of three sequential components: (1) Message Chunking, which decomposes an RFQ message into shorter items; (2) Few-shot Retrieval, which retrieves similar historical RFQs; and (3) Record Extraction, which generates structured RFQ records leveraging retrieved demonstrations. Compared with baseline methods, this approach delivers significant performance gains and exhibits superior adaptability to novel expressions. Building on this methodology, we developed Chat2Trade, a trading assistance system that parses RFQs and supports rapid filtering and querying. Chat2Trade transforms the brokers' traditional workflow from actively searching for relevant RFQs into a passive, real-time, push-based paradigm. The system has been deployed at China Securities, one of the largest securities firms in China, for nearly one year. It improves brokers' average trading volume by 3.67 times compared to traditional manual methods.

Image tagging, which assigns multiple tags to an image, is a crucial method for searching and managing large collections of images. Traditional image tagging tasks primarily focus on natural scene images. However, in recent years, with the development of digital art and AI image generation, the number of images dominated by virtual content has rapidly increased. These virtual content images often have new themes that emerge dynamically, while existing tagging methods rely on accessible tag sets for classification or matching and cannot discover new, unknown emerging tags. To address this issue, this paper proposes the dynamic image tagging task and introduces a generative tagging method based on Multi-Modal Large Language Models (MLLM). This method transforms image tagging from a classification or matching problem into a generation problem, utilizing MLLMs to extract topic keywords from images and then linking them to existing tags or identifying them as new emerging tags. This method can dynamically update and expand the tag set, effectively identifying emerging tags. To validate the effectiveness of the proposed method, we constructed a multi-modal virtual content tagging dataset. Experimental results demonstrate that the method presented in this paper can effectively discover emerging tags.

Recommendation systems are effective tools for information filtering and discovery. These systems are widely applied across various consumer sectors and hold significant potential for applications in professional domains to enhance work efficiency. However, supporting decision-making in professional contexts requires not only providing recommendation results but also offering explanations to persuade users to adopt the suggestions. Taking the task in the primary bond market as an example, where sales staff seek potential investors for bonds, this paper presents the development and deployment of a recommendation system designed for a professional setting. The system provides a set of key features as explanations for its recommendations. In this process, we observe that current explanation methods may select redundant and spurious features, which can undermine the persuasive impact of the explanations. To address this issue, we propose a method named ConciseExplain, which leverages a mask training strategy and gradient descent to directly identify a concise set of features. We conduct experiments on real-world and synthetic datasets. Our method achieves relative improvements of 6.1% and 12.4% over the best-performing baseline on redundant and spurious metrics, respectively. Our method also outperforms the baseline method in online manual evaluations. Moreover, during the one-year official deployment of our system at China Securities Co., Ltd. (a leading brokerage firm in China), we observed a continuous improvement in the accuracy of the recommendation system. This suggests that, with concise explanations, a positive feedback loop might be established between recommendation outcomes and investment decisions.

Detecting AI-involved text is essential for combating misinformation, plagiarism, and academic misconduct. However, AI text generation includes diverse collaborative processes (AI-written text edited by humans, human-written text edited by AI, and AI-generated text refined by other AI), where various or even new LLMs could be involved. Texts generated through these varied processes exhibit complex characteristics, presenting significant challenges for detection. Current methods model these processes rather crudely, primarily employing binary classification (purely human vs. AI-involved) or multi-classification (treating human-AI collaboration as a new class). We observe that representations of texts generated through different processes exhibit inherent clustering relationships. Therefore, we propose DETree, a novel approach that models the relationships among different processes as a Hierarchical Affinity Tree structure, and introduces a specialized loss function that aligns text representations with this tree. To facilitate this learning, we developed RealBench, a comprehensive benchmark dataset that automatically incorporates a wide spectrum of hybrid texts produced through various human-AI collaboration processes. Our method improves performance in hybrid text detection tasks and significantly enhances robustness and generalization in out-of-distribution scenarios, particularly in few-shot learning conditions, further demonstrating the promise of training-based approaches in OOD settings. Our code and dataset are available at https://github.com/heyongxin233/DETree.

Large language models (LLMs) can perform a new task by merely conditioning on task instructions and a few input-output examples, without optimizing any parameters.This is called In-Context Learning (ICL).In-context Information Extraction (IE) has recently garnered attention in the research community.However, the performance of In-context IE generally lags behind the state-of-the-art supervised expert models.We highlight a key reason for this shortfall: underspecified task description.The limited-length context struggles to thoroughly express the intricate instructions and various edge cases of IE tasks, leading to misalignment in task comprehension with humans.In this paper, we propose a Guideline Learning (GL) framework for In-context IE which reflectively learns and follows guidelines.During the learning phrase, GL automatically synthesizes a set of guidelines based on a few error cases, and during inference, GL retrieves helpful guidelines for better ICL.Moreover, we propose a self-consistency-based active learning method to enhance the efficiency of GL.Experiments on event extraction and relation extraction show that GL can significantly improve the performance of in-context IE.

Selective classification allows a machine learning model to reject some hard inputs and thus improve the reliability of its predictions. In this area, the ensemble method is powerful in practice, but there has been no solid analysis on why the ensemble method works. Inspired by an interesting empirical result that the improvement of the ensemble largely comes from top-ambiguity samples where its member models diverge, we prove that, based on some assumptions, the ensemble has a lower selective risk than the member model for any coverage within a range. The proof is nontrivial since the selective risk is a non-convex function of the model prediction. The assumptions and the theoretical results are supported by systematic experiments on both computer vision and natural language processing tasks.

Tables are omnipresent on the web and in various vertical domains, storing massive amounts of valuable data. However, the great flexibility in the table layout hinders the machine from understanding this valuable data. In order to unlock and utilize knowledge from tables, extracting data as numerical tuples is the first and critical step. As a form of relational data, numerical tuples have direct and transparent relationships between their elements and are therefore easy for machines to use. Extracting numerical tuples requires a deep understanding of intricate correlations between cells. The correlations are presented implicitly in texts and visual appearances of tables, which can be roughly classified into Hierarchy and Juxtaposition. Although many studies have made considerable progress in data extraction from tables, most of them only consider hierarchical relationships but neglect the juxtapositions. Meanwhile, they only evaluate their methods on relatively small corpora. This paper proposes a new framework to extract numerical tuples from tables and evaluate it on a large test set. Specifically, we convert this task into a relation extraction problem between cells. To represent cells with their intricate correlations in tables, we propose a BERT-based pre-trained language model, TableLM, to encode tables with diverse layouts. To evaluate the framework, we collect a large finance dataset that includes 19,264 tables and 604K tuples. Extensive experiments on the dataset are conducted to demonstrate the superiority of our framework compared to a well-designed baseline.

Research on automatically solving mathematical word problems (MWP) has a long history. Most recent works adopt Seq2Seq approach to predict the result equations as a sequence of quantities and operators. Although result equations can be written as a sequence, it is essentially a structure. More precisely, it is a Direct Acyclic Graph (DAG) whose leaf nodes are the quantities, and internal and root nodes are arithmetic or comparison operators. In this paper, we propose a novel Seq2DAG approach to extract the equation set directly as a DAG structure. It is extracted in a bottom-up fashion by aggregating quantities and sub-expressions layer by layer iteratively. The advantages of our approach approach are three-fold: it is intrinsically suitable to solve multivariate problems, it always outputs valid structure, and its computation satisfies commutative law for +, x and =. Experimental results on Math23K and DRAW1K demonstrate that our model outperforms state-of-the-art deep learning methods. We also conduct detailed analysis on the results to show the strengths and limitations of our approach.

The initial public offering (IPO) market in Hong Kong is consistently one of the largest in the world. As part of its regulatory responsibilities, Hong Kong Exchanges and Clearing Limited (HKEX) reviews annual reports published by listed companies (issuers). The number of issuers has grown at a fast pace, reaching 2,538 as the end of 2020. This poses a challenge for manually reviewing these annual reports against the many diverse regulatory obligations (listing rules). We propose a system named Jura to improve the efficiency of annual report reviewing with the help of machine learning methods. This system checks the compliance of an issuer's published information against listing rules in four steps: panoptic document recognition, relevant passage location, fine-grained information extraction, and compliance assessment. This paper introduces in detail the passage location step, how it is critical for speeding up compliance assessment, and the various challenges faced. We argue that although a passage is a relatively independent unit, it needs to be combined with document structure and contextual information to accurately locate the relevant passages. With the help of Jura, HKEX reports saving 80% of the time on reviewing issuers' annual reports.

Claims over the numerical relationships among some measures are commonly expressed in tabular forms, and widely exist in the published documents on the Web. This paper introduces the problem of numerical formula recognition from tables, namely recognizing all numerical formulas inside a given table. It can well support many interesting downstream applications, such as numerical error correction in tables, formula recommendation in tables. Here, we emphasize that table is a kind of language that adopts a different linguistic paradigm from natural language. It uses visual grammar like visual layout and visual settings (e.g., indentation, font style) to express the grammatical relationships among the table cells. Understanding tables and recognizing formulas require decoding the visual grammar while simultaneously understanding the textual information. Another challenge is that formulas are complicated in terms of diverse math functions and variable-length of arguments. To address these challenges, we convert this task into a uniform framework, extracting relations of table cell pairs in a table. A two-channel neural network model TaFor is proposed to embed both the textual and visual features for a table cell. Our framework achieves the formula-level F1-score = 0.90 on a real-world dataset of 190179 tables while a retrieval-based method achieves F1-score = 0.72. We also perform extensive experiments to demonstrate the effectiveness of each component in our model, and conduct a case study to discuss the limits of the proposed model. With our published data this study also aims to attract the community's interest in deep semantic understanding over tables.

Tabular forms of numerical facts widely exist in the disclosure documents of vertical domains, especially the financial fields. It is also quite common that the same fact might be mentioned multiple times in different tables with diverse tabular presentation. Firm's disclosure documents are the main source of accounting information for individual investors. Its authenticity is crucial for both firms' development and investors' investment decisions. However, due to large volumes of tables, frequent updates during editing, and limited time for manual cross-checking, these facts might be inconsistent with each other even after official publishing. Such errors may bring about huge reputational risk, and even economic losses even if the mistakes are made unintentionally instead of deliberately. Hence, it creates an opportunity for Automatic Numerical Cross-Checking over Tables. This paper introduces the key module of such a system, which aims to identify whether a pair of table cells are semantically equivalent, namely referring to the same fact. We observed that due to tabular presentation diversity the facts in tabular forms are difficult to be parsed into relational tuples. Thus, we present an end-to-end solution of binary classification over each pair of table cells, which does not involve with explicit semantic parsing over tables. Also, we discuss the design of this neural model to compromise between prediction accuracy and inference time for a large number of table cell pairs, and propose some practical techniques to address the issue of extreme classification imbalance among pairs. Experiments show that our model achieves macro F1 = 0.8297 in linking semantically equivalent table cells from the IPO prospectus. Finally, an auditing tool is built to support guided cross-checking over financial documents, reducing work hours by 52% ~ 68%. This system has received wide recognition in the Chinese financial community. Nine of the top ten Chinese security brokers have adopted this system to support their business of investment banking.

Natural language is used to describe objective facts, including simple relations like ""Jobs was the CEO of Apple"", and complex relations like ""the GDP of the United States in 2018 grew 2.9% compared with 2017". For the latter example, the growth rate relation is between two other relations. Due to the complex nature of language, this kind of nested relations is expressed frequently, especially in professional documents in fields like economics, finance, and biomedicine. But extracting nested relations is challenging, and research on this problem is almost vacant. In this paper, we formally formulate the nested relation extraction problem, and come up with a solution using Iterative Neural Network. Specifically, we observe that the nested relation structures can be expressed as a Directed Acyclic Graph (DAG), and propose the model to simultaneously consider the word sequence of natural language in the horizontal direction and the DAG structure in the vertical direction. Based on two nested relation extraction tasks, namely semantic causality relation extraction and formula extraction, we show that the proposed model works well on them. Moreover, we speed up the DAG-LSTM training significantly by a simple parallelization solution.

Verbal descriptions over the numerical relationships among some objective measures widely exist in the published documents on Web, especially in the financial fields. However, due to large volumes of documents and limited time for manual cross-check, these claims might be inconsistent with the original structured data of the related indicators even after official publishing. Such errors can seriously affect investors' assessment of the company and may cause them to undervalue the firm even if the mistakes are made unintentionally instead of deliberately. It creates an opportunity for automated Numerical Cross-Checking (NCC) systems. This paper introduces the key component of such a system, formula extractor, which extracts formulas from verbal descriptions of numerical claims. Specifically, we formulate this task as a DAG-structure prediction problem, and propose an iterative relation extraction model to address it. In our model, we apply a bi-directional LSTM followed by a DAG-structured LSTM to extract formulas layer by layer iteratively. Then, the model is built using a human-labeled dataset of tens of thousands of sentences. The evaluation shows that this model is effective in formula extraction. At the relation level, the model achieves a 97.78% precision and 98.33% recall. At the sentence level, the predictions over 92.02% of sentences are perfect. Overall, the project for NCC has received wide recognition in the Chinese financial community.