The rapid spread of multimodal fake news poses a serious societal threat, as its evolving nature and reliance on timely factual details challenge existing detection methods. Dynamic Retrieval-Augmented Generation provides a promising solution by triggering keyword-based retrieval and incorporating external knowledge, thus enabling both efficient and accurate evidence selection. However, it still faces challenges in addressing issues such as redundant retrieval, coarse similarity, and irrelevant evidence when applied to deceptive content. In this paper, we propose ExDR—an Explanation-driven Dynamic Retrieval-Augmented Generation framework for Multimodal Fake News Detection. Our framework systematically leverages model-generated explanations in both the retrieval triggering and evidence retrieval modules. It assesses triggering confidence from three complementary dimensions, constructs entity-aware indices by fusing deceptive entities, and retrieves contrastive evidence based on deception-specific features to challenge the initial claim and enhance the final prediction. Experiments on two benchmark datasets, AMG and MR2, demonstrate that ExDR consistently outperforms previous methods in retrieval triggering accuracy, retrieval quality, and overall detection performance, highlighting its effectiveness and generalization capability.

Recent progress in large language model (LLM) based generative recommendation (GR) shows that leveraging LLM world knowledge can substantially improve performance. However, existing methods rely on fixed, manually designed instructions to generate semantic knowledge and directly incorporate it into GR, which has two limitations: (1) fixed instructions cannot capture the multidimensional heterogeneity of user interests; (2) uncontrollable knowledge fusion may conflict with behavioral signals and harm recommendations. To address these limitations, we propose LWGR, a framework that leverages Lagrangian constraints to transfer users' personalized World knowledge from LLMs into Generative Recommendation. LWGR enhances GR along two axes: knowledge extraction and fusion. It builds user personalized soft instructions to extract behavior-relevant LLM world knowledge. Then, it formulates knowledge fusion as an optimization problem with explicitly bounded performance degradation, solved via a Lagrangian primal–dual method that selectively incorporates beneficial knowledge. We further design two training strategies for different LLM scales and a deployment scheme that combines nearline precomputation with lightweight online serving. Experiments on multiple public datasets and one industrial dataset show that LWGR outperforms eight state-of-the-art baselines by up to 11.23% and brings a 1.35% revenue lift on a large-scale advertising platform, demonstrating its effectiveness and practicality.

Sarcasm Explanation in Dialogue (SED) task aims to uncover the underlying meaning of sarcastic expressions in multimodal dialogues. While previous studies have largely focused on modeling dialogue content, they often neglect the influence of speakers and the interactions between utterances. To address this gap, we propose a novel framework called CISI, which integrates personalized communication styles, inter-speaker interaction relationships, and sarcasm-centric multimodal cues to enhance SED. To capture how personalized styles influence sarcasm expression, we model speakers' communication styles using Satir's Communication Model in psychology. Furthermore, we model the flow of sarcasm through discourse parsing, constructing explicit conversational interaction and dependencies between speakers. Lastly, we design a multimodal fusion module that aligns modality-specific cues with sarcasm-related semantics to enhance understanding. Extensive experiments on the WITS dataset demonstrate that CISI achieves superior performance. We also obtain competitive results on the MUStARD dataset for dialogue-level multimodal sarcasm detection, further showcasing the generalizability of CISI.

In recent years, the study on defending deep hashing models against adversarial attacks has garnered increasing attention. Among them, adversarial training is an effective method to train robust deep hashing models. Existing adversarial training methods for deep hashing simultaneously optimize original deep hashing loss and proposed adversarial training loss to train a robust model. However, we argue that directly using the original deep hashing loss will guide the model to learn excessive non-robust patterns from clean examples when extracting discriminative semantic information, thereby limiting model robustness. To tackle this, we propose a novel Clean model Representation Distillation based Adversarial Training (CRDAT) method, which enables the robust model to learn both discriminative semantic information and robust patterns by separating these two losses into two stages, i.e., standard training stage of a clean teacher model and adversarial training stage of a robust student model. Specifically, we propose a novel representation distillation based adversarial training loss, which distills the representations of the teacher model on clean examples at both the hash code level and feature level to guide the student model's learning on adversarial examples. Extensive experiments on multiple datasets and deep hashing methods demonstrate that our CRDAT method can greatly improve model robustness and achieve state-of-the-art defense performance.

Large language models (LLMs) achieve superior performance in generative tasks. However, due to the natural gap between language model generation and structured information extraction in three dimensions: task type, output format, and modeling granularity, they often fall short in structured information extraction, a crucial capability for effective data utilization on the web. In this paper, we define the generation process of the language model as the controllable state transition, aligning the generation and extraction processes to ensure the integrity of the output structure and adapt to the goals of the information extraction task. Furthermore, we propose the Structure2Text decider to help the language model understand the fine-grained extraction information, which converts the structured output into natural language and makes state decisions, thereby focusing on the task-specific information kernels, and alleviating language model hallucinations and incorrect content generation. We conduct extensive experiments and detailed analyses on myriad information extraction tasks, including named entity recognition, relation extraction, and event argument extraction. Our method not only achieves significant performance improvements but also considerably enhances the model's capability to generate precise and relevant content, making the extracted content easy to parse.

Data augmentation has been widely studied as it can be used to improve the generalizability of graph representation learning models. However, existing works focus only on the data augmentation on homogeneous graphs. Data augmentation for heterogeneous graphs remains under-explored. Considering that heterogeneous graphs contain different types of nodes and links, ignoring the type information and directly applying the data augmentation methods of homogeneous graphs to heterogeneous graphs will lead to suboptimal results. In this paper, we propose a novel Multi-Aspect Heterogeneous Graph Augmentation framework named MAHGA. Specifically, MAHGA consists of two core augmentation strategies: structure-level augmentation and metapath-level augmentation. Structure-level augmentation pays attention to network schema aspect and designs a relation-aware conditional variational auto-encoder that can generate synthetic features of neighbors to augment the nodes and the node types with scarce links. Metapath-level augmentation concentrates on metapath aspect, which constructs metapath reachable graphs for different metapaths and estimates the graphons of them. By sampling and mixing up based on the graphons, MAHGA yields intra-metapath and inter-metapath augmentation. Finally, we conduct extensive experiments on multiple benchmarks to validate the effectiveness of MAHGA. Experimental results demonstrate that our method improves the performances across a set of heterogeneous graph learning models and datasets.

Recommender systems which captures dynamic user interest based on time-ordered user-item interactions plays a critical role in the real-world. Although existing deep learning-based recommendation systems show good performances, these methods have two main drawbacks. Firstly, user interest is the consequence of the coaction of many factors. However, existing methods do not fully explore potential influence factors and ignore the user-item interaction formation process. The coarse-grained modeling patterns cannot accurately reflect complex user interest and leads to suboptimal recommendation results. Furthermore, these methods are implicit and largely operate in a black-box fashion. It is difficult to interpret their modeling processes and recommendation results. Secondly, recommendation datasets usually exhibit scale-free distributions and some existing recommender systems take advantage of hyperbolic space to match the data distribution. But they ignore that the operations in hyperbolic space are more complex than that in Euclidean space which further increases the difficulty of model interpretation. To tackle the above shortcomings, we propose an E xplainable H yperbolic T emporal P oint P rocess for User-Item Interaction Sequence Generation (EHTPP) . Specifically, EHTPP regards each user-item interaction as an event in hyperbolic space and employs a temporal point process framework to model the probability of event occurrence. Considering that the complexity of user interest and the interpretability of the model,EHTPP explores four potential influence factors related to user interest and uses them to explicitly guide the probability calculation in the temporal point process. In order to validate the effectiveness of EHTPP, we carry out a comprehensive evaluation of EHTPP on three datasets compared with a few competitive baselines. Experimental results demonstrate the state-of-the-art performances of EHTPP.

Paraphrase generation can be modeled as a sequence-to-sequence (Seq2Seq) learning problem. Nonetheless, a typical Seq2Seq model is liable to convey the original meaning incorrectly, as the vectorial representation of the given sentence is sometimes inadequate in recapitulating complicated semantic. Naturally, paraphrases concern the same topic, which can serve as an auxiliary guidance to promote the preservation of source semantic. Moreover, some interesting words for restatements can be derived from the topical information. To exploit topic in paraphrase generation, we incorporate topic words into the Seq2Seq framework through a topic-aware input and a topic-biased generation distribution. Direct supervision signals are also introduced to help dealing with the topic information more accurately. Empirical studies on two benchmark datasets show that the proposed method significantly improves the basic Seq2Seq model, and it is comparable with the state-of-the-art systems.

One of the most challenging tasks in large-scale multi-label image retrieval is to map images into binary codes while preserving multilevel semantic similarity. Recently, several deep supervised hashing methods have been proposed to learn hash functions that preserve multilevel semantic similarity with deep convolutional neural networks. However, these triplet label based methods try to preserve the ranking order of images according to their similarity degrees to the queries while not putting direct constraints on the distance between the codes of very similar images. Besides, the current evaluation criteria are not able to measure the performance of existing hashing methods on preserving fine-grained multilevel semantic similarity. To tackle these issues, we propose a novel Deep Multilevel Semantic Similarity Preserving Hashing (DMSSPH) method to learn compact similarity-preserving binary codes for the huge body of multi-label image data with deep convolutional neural networks. In our approach, we make the best of the supervised information in the form of pairwise labels to maximize the discriminability of output binary codes. Extensive evaluations conducted on several benchmark datasets demonstrate that the proposed method significantly outperforms the state-of-the-art supervised and unsupervised hashing methods at the accuracies of top returned images, especially for shorter binary codes. Meanwhile, the proposed method shows better performance on preserving fine-grained multilevel semantic similarity according to the results under the Jaccard coefficient based evaluation criteria we propose.

Sentiment analysis in various languages has been a research hotspot with many applications. However, sentiment resources (e.g., labeled corpora, sentiment lexicons) of different languages are unbalanced in terms of quality and quantity, which arouses interests in cross-lingual sentiment analysis aiming at using the resources in a source language to improve sentiment analysis in a target language. Nevertheless, many existing cross-lingual related works rely on a certain machine translation system to directly adapt the labeled data from the source language to the target language, which usually suffers from inaccurate results generated by the machine translation system. On the other hand, most sentiment analysis studies focus on document-level sentiment classification that cannot solve the aspect dependency problem of sentiment words. For instance, in the reviews on a cell phone, long is positive for the lifespan of its battery, but negative for the response time of its operating system. To solve these problems, this paper develops a novel Cross-Lingual Joint Aspect/Sentiment (CLJAS) model to carry out aspect-specific sentiment analysis in a target language using the knowledge learned from a source language. Specifically, the CLJAS model jointly detects aspects and sentiments of two languages simultaneously by incorporating sentiments into a cross-lingual topic model framework. Extensive experiments on different domains and different languages demonstrate that the proposed model can significantly improve the accuracy of sentiment classification in the target language.

Bilingual sentiment lexicon is fundamental resource for cross-language sentiment analysis but its compilation remains a major bottleneck in computational linguistics. Traditional word alignment algorithm faces with the status of large alignment space, which may introduce redundant computations as well as alignment errors. In this paper, we use collocation alignment to extract bilingual sentiment lexicon overcoming the drawbacks of word alignment. The idea of collocation alignment is inspired by the strong cohesion between feature words and opinion words in sentiment corpus. Experimental results show that our approach not only decreases the computing time dramatically but also improves the precision of extracted bilingual word pairs due to the smaller alignment space.

In this paper, we aim to jointly extract aspects and aspect-specific sentiment knowledge from online reviews, where the sentiment knowledge refers to the aspect-specific opinion words along with their aspect-aware sentiment polarities. To this end, we propose a Joint Aspect/Sentiment model (JAS). JAS detects aspect-specific opinion words by integrating opinion word lexicon knowledge to explicitly separate opinion words from factual words. More importantly, JAS exploits sentiment prior and aspect-contextual sentence-level co-occurrences of opinion words in reviews to further identify aspect-aware sentiment polarities for the opinion words. We apply the learned aspect-specific sentiment knowledge to practical aspect-level sentiment analysis tasks. Experimental results show the effectiveness of JAS in learning aspect-specific sentiment knowledge and the practical value of this knowledge when applied to aspect-level sentiment classification.

The explosion of multilingual opinion data has made essential the need for automatic tools to analyze and understand people's opinions in multilingual reviews. In cross-language opinion mining, bilingual opinion lexicon plays a central role. Most of the bilingual lexicon extraction methods are based on EM algorithm. However, these methods are faced with two major problems: high complexity and unsatisfying precision. In this paper, we propose a novel approach to extract bilingual opinion lexicon using collocation alignment, where a collocation is a combination of a feature word and an opinion word. There are tight association between feature words and opinion words, which can be helpful to reduce the computation space and alignment errors. Experimental results demonstrate that our solution is effective and competitive.

This paper aims to find blog feeds having a principal inclination towards making opinionated comments on the given topic, so that we can subscribe to them to track influential and interesting opinions in the blogosphere. One major challenge is assigning topic-related opinion scores to blog feeds, which is embodied in two aspects. Firstly, we should identify whether the blog feed has a principal on-topic opinionated inclination. This inclination should be collectively revealed by all posts of the feed. We should fully consider evidences from all the posts of the feed to identify salient information among many posts of the feed. Secondly, we should capture topic-related opinions in the blog feed while ignoring irrelevant opinions.

Many methods for cross-lingual processing tasks are resource-dependent, which will not work without machine translation system or bilingual lexicon. In this paper, we propose a novel approach for multilingual sentiment classification just by few seed words. For a given language, the proposed approach learns a sentiment classifier from the initial seed words instead of any labeled data. We employ our method both in supervised learning and unsupervised learning. Experimental results demonstrate that our method relies less on external resource but performs as well as or better than the baseline.