Current multimodal large language models (MLLMs) still face significant challenges in complex visual tasks (e.g., spatial understanding, fine-grained perception). Prior methods have tried to incorporate visual reasoning, however, they fail to leverage attention correction with spatial cues to iteratively refine their focus on prompt-relevant regions. In this paper, we introduce SIFThinker, a spatially-aware “think-with-images” framework that mimics human visual perception. Specifically, SIFThinker enables attention correcting and image region focusing by interleaving depth-enhanced bounding boxes and natural language. Our contributions are twofold: First, we introduce a reverse-expansion-forward-inference strategy that facilitates the generation of interleaved image-text chains of thought for process-level supervision, which in turn leads to the construction of the SIF-50K dataset. Besides, we propose GRPO-SIF, a reinforced training paradigm that integrates depth-informed visual grounding into a unified reasoning pipeline, teaching the model to dynamically correct and focus on prompt-relevant regions. Extensive experiments demonstrate that SIFThinker outperforms state-of-the-art methods in spatial understanding and fine-grained visual perception, while maintaining strong general capabilities, highlighting the effectiveness of our method.

Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaopu Wu, Kai Xiong, Qingsong Liu, Guoliang Kang, Yangyang Kang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Graph-level representations are critical in various real-world applications, such as predicting the properties of molecules. However, in practice, precise graph annotations are generally very expensive and time-consuming. To address this issue, graph contrastive learning constructs an instance discrimination task, which pulls together positive pairs (augmentation pairs of the same graph) and pushes away negative pairs (augmentation pairs of different graphs) for unsupervised representation learning. However, since for a query, its negatives are uniformly sampled from all graphs, existing methods suffer from the critical sampling bias issue, i.e., the negatives likely having the same semantic structure with the query, leading to performance degradation. To mitigate this sampling bias issue, in this article, we propose a prototypical graph contrastive learning (PGCL) approach. Specifically, PGCL models the underlying semantic structure of the graph data via clustering semantically similar graphs into the same group and simultaneously encourages the clustering consistency for different augmentations of the same graph. Then, given a query, it performs negative sampling via drawing the graphs from those clusters that differ from the cluster of query, which ensures the semantic difference between query and its negative samples. Moreover, for a query, PGCL further reweights its negative samples based on the distance between their prototypes (cluster centroids) and the query prototype such that those negatives having moderate prototype distance enjoy relatively large weights. This reweighting strategy is proven to be more effective than uniform sampling. Experimental results on various graph benchmarks testify the advantages of our PGCL over state-of-the-art methods. The code is publicly available at https://github.com/ha-lins/PGCL.

Event causality identification (ECI) aims to identify the causal relationship between events, which plays a crucial role in deep text understanding. Due to the diversity of real-world causality events and difficulty in obtaining sufficient training data, existing ECI approaches have poor generalizability and struggle to identify the relation between seldom seen events. In this paper, we propose to utilize both external knowledge and internal analogy to improve ECI. On the one hand, we utilize a commonsense knowledge graph called ConceptNet to enrich the description of an event sample and reveal the commonalities or associations between different events. On the other hand, we retrieve similar events as analogy exam- ples and glean useful experiences from such analogous neigh- bors to better identify the relationship between a new event pair. By better understanding different events through exter- nal knowledge and making an analogy with similar events, we can alleviate the data sparsity issue and improve model gener- alizability. Extensive evaluations on two benchmark datasets show that our model outperforms other baseline methods by around 18% on the F1-value on average

Credit card fraud incurs a considerable cost for both cardholders and issuing banks. Contemporary methods apply machine learning-based classifiers to detect fraudulent behavior from labeled transaction records. But labeled data are usually a small proportion of billions of real transactions due to expensive labeling costs, which implies that they do not well exploit many natural features from unlabeled data. Therefore, we propose a semi-supervised graph neural network for fraud detection. Specifically, we leverage transaction records to construct a temporal transaction graph, which is composed of temporal transactions (nodes) and interactions (edges) among them. Then we pass messages among the nodes through a Gated Temporal Attention Network (GTAN) to learn the transaction representation. We further model the fraud patterns through risk propagation among transactions. The extensive experiments are conducted on a real-world transaction dataset and two publicly available fraud detection datasets. The result shows that our proposed method, namely GTAN, outperforms other state-of-the-art baselines on three fraud detection datasets. Semi-supervised experiments demonstrate the excellent fraud detection performance of our model with only a tiny proportion of labeled data.

Medical insurance plays a vital role in modern society, yet organized healthcare fraud causes billions of dollars in annual losses, severely harming the sustainability of the social welfare system. Existing works mostly focus on detecting individual fraud entities or claims, ignoring hidden conspiracy patterns. Hence, they face severe challenges in tackling organized fraud. In this paper, we proposed RDPGL, a novel Risk Diffusion-based Parallel Graph Learning approach, to fighting against medical insurance criminal gangs. In particular, we first leverage a heterogeneous graph attention network to encode the local context from the beneficiary-provider graph. Then, we devise a community-aware risk diffusion model to infer the global context of organized fraud behaviors with the claim-claim relation graph. The local and global representations are parallel concatenated together and trained simultaneously in an end-to-end manner. Our approach is extensively evaluated on a real-world medical insurance dataset. The experimental results demonstrate the superiority of our proposed approach, which could detect more organized fraud claims with relatively high precision compared with state-of-the-art baselines.

Chinese Spelling Correction (CSC) is gaining increasing attention in recent years. Despite its extensive use in many applications, such as search engine and optical character recognition system, little has been explored in medical scenarios in which complex and uncommon medical entities are easily misspelled. Correcting the misspellings of medical entities is arguably more difficult than those in the open domain due to its requirements of specific domain knowledge. In this work, we define the task of Medical-domain Chinese Spelling Correction (MCSC) and propose MCSCSet, a large-scale specialist-annotated dataset that contains about 200k samples. In contrast to existing open-domain CSC datasets, MCSCSet involves: i) extensive real-world medical queries collected from Tencent Yidian, ii) corresponding misspelled sentences manually annotated by medical specialists. Our work further offers a medical-domain confusion set consisting of the common error-prone characters in medicine and their corresponding misspellings. Extensive empirical studies have shown significant gaps between the open-domain and medical-domain spelling correction, highlighting the need to develop high-quality datasets that allow for CSC in specific domains. Moreover, our work benchmarks several representative methods, establishing baselines for future work.

Providing Emotional Support (ES) to soothe people in emotional distress is an essential capability in social interactions.Most existing research on building ES conversation systems only considers single-turn interactions with users, which is over-simplified.In comparison, multi-turn ES conversation systems can provide ES more effectively, but face several new technical challenges, including: i) how to conduct support strategy planning that could lead to the best supporting effects; ii) how to dynamically model the user's state.In this paper, we propose a novel system named MultiESC to address these issues.For strategy planning, drawing inspiration from the A* search algorithm, we propose lookahead heuristics to estimate the future user feedback after using particular strategies, which helps to select strategies that can lead to the best long-term effects.For user state modeling, MultiESC focuses on capturing users' subtle emotional expressions and understanding their emotion causes.Extensive experiments show that MultiESC significantly outperforms competitive baselines in both strategy planning and dialogue generation.Our codes are available at https: //github.com/lwgkzl/MultiESC.

Recent years have witnessed the dramatic growth of paper volumes with plenty of new research papers published every day, especially in the area of computer science. How to glean papers worth reading from the massive literature to do a quick survey or keep up with the latest advancement about a specific research topic has become a challenging task. Existing academic search engines return relevant papers by individually calculating the relevance between each paper and query. However, such systems usually omit the prerequisite chains of a research topic and cannot form a meaningful reading path. In this paper, we introduce a new task named Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query. To serve as a research benchmark, we further propose SurveyBank, a dataset consisting of large quantities of survey papers in the field of computer science as well as their citation relationships. Furthermore, we propose a graph-optimization-based approach for reading path generation which takes the relationship between papers into account. Extensive evaluations demonstrate that our approach outperforms other baselines. A real-time Reading Path Generation (RePaGer) system has been also implemented with our designed model. Our source code and SurveyBank dataset can be found here11https://github.com/JiayuanDing100/Reading-Path-Generation.

With the rise of telemedicine, the task of developing Dialogue Systems for Medical Diagnosis (DSMD) has received much attention in recent years. Different from early researches that needed to rely on extra human resources and expertise to build the system, recent researches focused on how to build DSMD in a data-driven manner. However, the previous data-driven DSMD methods largely overlooked the system interpretability, which is critical for a medical application, and they also suffered from the data sparsity issue at the same time. In this paper, we explore how to bring interpretability to data-driven DSMD. Specifically, we propose a more interpretable decision process to implement the dialogue manager of DSMD by reasonably mimicking real doctors' inquiry logics, and we devise a model with highly transparent components to conduct the inference. Moreover, we collect a new DSMD dataset, which has a much larger scale, more diverse patterns, and is of higher quality than the existing ones. The experiments show that our method obtains 7.7%, 10.0%, 3.0% absolute improvement in diagnosis accuracy respectively on three datasets, demonstrating the effectiveness of its rational decision process and model design. Our codes and the GMD-12 dataset are available at https://github.com/lwgkzl/BR-Agent.

Taxonomy is a fundamental type of knowledge graph for a wide range of web applications like searching and recommendation systems. To keep a taxonomy automatically updated with the latest concepts, the taxonomy completion task matches a pair of proper hypernym and hyponym in the original taxonomy with the new concept as its parent and child. Previous solutions utilize term embeddings as input and only evaluate the parent-child relations between the new concept and the hypernym-hyponym pair. Such methods ignore the important sibling relations, and are not applicable in reality since term embeddings are not available for the latest concepts. They also suffer from the relational noise of the “pseudo-leaf” node, which is a null node acting as a node’s hyponym to enable the new concept to be a leaf node. To tackle the above drawbacks, we propose the Quadruple Evaluation Network (QEN), a novel taxonomy completion framework that utilizes easily accessible term descriptions as input, and applies pretrained language model and code attention for accurate inference while reducing online computation. QEN evaluates both parent-child and sibling relations to both enhance the accuracy and reduce the noise brought by pseudo-leaf. Extensive experiments on three real-world datasets in different domains with different sizes and term description sources prove the effectiveness and robustness of QEN on overall performance and especially the performance for adding non-leaf nodes, which largely surpasses previous methods and achieves the new state-of-the-art of the task.1

With the rapid development of cloud manufacturing, industrial production with edge computing as the core architecture has been greatly developed. However, edge devices often suffer from abnormalities and failures in industrial production. Therefore, detecting these abnormal situations timely and accurately is crucial for cloud manufacturing. As such, a straightforward solution is that the edge device uploads the data to the cloud for anomaly detection. However, Industry 4.0 puts forward higher requirements for data privacy and security so that it is unrealistic to upload data from edge devices directly to the cloud. Considering the abovementioned severe challenges, this article customizes a weakly supervised edge computing anomaly detection framework, i.e., federated learning-based transformer framework (FedAnomaly), to deal with the anomaly detection problem in cloud manufacturing. Specifically, we introduce federated learning (FL) framework that allows edge devices to train an anomaly detection model in collaboration with the cloud without compromising privacy. To boost the privacy performance of the framework, we add differential privacy noise to the uploaded features. To further improve the ability of edge devices to extract abnormal features, we use the transformer to extract the feature representation of abnormal data. In this context, we design a novel collaborative learning protocol to promote efficient collaboration between FL and transformer. Furthermore, extensive case studies on four benchmark datasets verify the effectiveness of the proposed framework. To the best of our knowledge, this is the first time integrating FL and transformer to deal with anomaly detection problems in cloud manufacturing.

Federated Edge Learning (FEL) allows edge nodes to train a global deep learning model collaboratively for edge computing in the Industrial Internet of Things (IIoT), which significantly promotes the development of Industrial 4.0. However, FEL faces two critical challenges: communication overhead and data privacy. FEL suffers from expensive communication overhead when training large-scale multi-node models. Furthermore, due to the vulnerability of FEL to gradient leakage and label-flipping attacks, the training process of the global model is easily compromised by adversaries. To address these challenges, we propose a communication-efficient and privacy-enhanced asynchronous FEL framework for edge computing in IIoT. First, we introduce an asynchronous model update scheme to reduce the computation time that edge nodes wait for global model aggregation. Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes. Third, we design a cloud-side malicious node detection mechanism to detect malicious nodes by testing the local model quality. Such a mechanism can avoid malicious nodes participating in training to mitigate label-flipping attacks. Extensive experimental studies on two real-world datasets demonstrate that the proposed framework can not only improve communication efficiency but also mitigate malicious attacks while its accuracy is comparable to traditional FEL frameworks.

Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the prior disease-symptom relations. Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues. More importantly, by dynamically evolving disease-symptom graphs, GEML also well addresses the real-world challenges that the disease-symptom correlations of each disease may vary or evolve along with more diagnostic cases. Extensive experiment results on the CMDD dataset and our newly-collected Chunyu dataset testify the superiority of our approach over state-of-the-art approaches. Besides, our GEML can generate an enriched dialogue-sensitive knowledge graph in an online manner, which could benefit other tasks grounded on knowledge graph.

Yi Cheng, Siyao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, Yefeng Zheng. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Zijing Ou, Qinliang Su, Jianxing Yu, Bang Liu, Jingwen Wang, Ruihui Zhao, Changyou Chen, Yefeng Zheng. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Federated Learning (FL) is a privacy-oriented framework that allows distributed edge devices to jointly train a shared global model without transmitting their sensed data to centralized servers. FL aims to balance the naturally conflicting objectives of obtaining massive amounts of data while protecting sensitive information. However, the data stored locally on each edge device are typically not independent and identically distributed (non-IID). Such data heterogeneity poses a severe statistical challenge for the optimization and convergence of the global model. In response to this issue, we propose Federated One-vs-All (FedOVA), an efficient FL algorithm that first decomposes a multi-class classification problem into more straightforward binary classification problems and then combines their respective outputs using ensemble learning. Experiments on several public datasets show that FedOVA achieves higher accuracy and faster convergence than federated averaging and data sharing. Furthermore, our approach can support practical settings with a large number of clients (up to 1000 clients) in FL.

Zhengxu Hou, Bang Liu, Ruihui Zhao, Zijing Ou, Yafei Liu, Xi Chen, Yefeng Zheng. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence. The taxonomy expansion task aims to find a position for a new term in an existing taxonomy to capture the emerging knowledge in the world and keep the taxonomy dynamically updated. Previous taxonomy expansion solutions neglect valuable information brought by the hierarchical structure and evaluate the correctness of merely an added edge, which downgrade the problem to node-pair scoring or mini-path classification. In this paper, we propose the Hierarchy Expansion Framework (HEF), which fully exploits the hierarchical structure’s properties to maximize the coherence of expanded taxonomy. HEF makes use of taxonomy’s hierarchical structure in multiple aspects: i) HEF utilizes subtrees containing most relevant nodes as self-supervision data for a complete comparison of parental and sibling relations; ii) HEF adopts a coherence modeling module to evaluate the coherence of a taxonomy’s subtree by integrating hypernymy relation detection and several tree-exclusive features; iii) HEF introduces the Fitting Score for position selection, which explicitly evaluates both path and level selections and takes full advantage of parental relations to interchange information for disambiguation and self-correction. Extensive experiments show that by better exploiting the hierarchical structure and optimizing taxonomy’s coherence, HEF vastly surpasses the prior state-of-the-art on three benchmark datasets by an average improvement of 46.7% in accuracy and 32.3% in mean reciprocal rank.