Document-level event factuality identification (DEFI) assesses the veracity degree to which an event mentioned in a document has happened, which is crucial for many natural language processing tasks. Previous work assesses event factuality by solely relying on the semantic information within a single document, which fails to identify hard cases where the document itself is hallucinative or counterfactual. There is also a pressing need for more suitable data of this kind. To tackle these issues, we construct Factualusion, a novel corpus with hallucination features that can be used not only for DEFI but can also be applied for hallucination evaluation for large language models. We further propose Trucidator, a graph-based framework that constructs intra-document and cross-document graphs and employs a multi-task learning paradigm to acquire more robust node embeddings, leveraging cross-document inference for more accurate identification. Experiments show that our proposed framework outperformed several baselines, demonstrating the effectiveness of our method.

Rumor detection is to identify and verify the authenticity of information to distinguish between true and false statements. For various types of rumors on social media, there is currently a lack of methods that effectively handle either unimodal or multimodal information simultaneously. Additionally, previous methods also suffered from the lack of images, the inconsistencies between the textual and visual modalities, and those misleading images. To address the above issues, we propose a Universal Rumor Detection Method (URDM), which introduces adversarial training using Diffusion and CLIP to enforce modality consistency and adopts Large Language Models (LLMs) and CoT (Chain of Thought) to generate external knowledge. Specifically, to address the issues of the missing modality and the inconsistencies between text and images, we introduce a random time step fine-tuning method for the Diffusion model to improve CLIP’s ability to judge text-image consistency, and enhance Diffusion’s accuracy in generating images based on text. Concurrently, we incorporated the CoT to serve as an extension of external knowledge to address the issue of misleading images. The experimental results on two popular datasets demonstrate that our proposed URDM outperforms the state-of-the-art baselines.

The proliferation of fake news videos on social media has heightened the demand for credible verification systems. While existing methods focus on detecting false content, generating human-readable explanations for such predictions remains a critical challenge. Current approaches suffer from spurious correlations caused by two key confounders: 1) video object bias, where co-occurring objects entangle features leading to incorrect semantic associations; and 2) explanation aspect bias, where models over-rely on frequent aspects while neglecting rare ones. To address these issues, we propose CIFE, a causal inference framework that disentangles confounding factors to generate unbiased explanations. First, we formalize the problem through a Structural Causal Model (SCM) to identify confounding factors. We then introduce two novel modules: 1) the Interventional Video-Object Detector (IVOD), which employs backdoor adjustment to decouple object-level visual semantics; and 2) the Interventional Explanation Aspect Module (IEAM), which balances aspect selection during multimodal fusion. Extensive experiments on the FakeVE dataset demonstrate the effectiveness of CIFE, which generates more faithful explanations by mitigating object entanglement and aspect imbalance. Our code is available at https://github.com/Lieberk/CIFE.

This paper concentrates on Document-level Event Factuality Identification (DEFI) that predicts event factuality values from the viewpoint of the document. At present, the shortcomings of previous studies are multi-fold, including data limitation and scarcity, coarsegrained interpretability without span-level factuality clues, no unified model for different datasets. This paper is devoted to address the above problems by building unified Machine Reading Comprehension (MRC) frameworks comprised of both span-extraction and multiple-choice styles, which exploit Heterogeneous Spectral Attention Networks (HSAN) with spectral networks and hypergraph attention networks as the fine-grained encoders, especially for span-level encoding. Moreover, we integrate Transfer Learning (TL) as cross-domain data augmentation to learn more span-level information from classical MRC datasets by source and target adapters. Experimental performance on ExDLEF corpus, which contains both English and Chinese documents, shows that our span-extraction MRC model is superior to several state-of-the-art baselines, and proves the effectiveness of transfer learning under MRC paradigms.

Rumors on social media can spread rapidly and widely with the help of the Internet characteristics, causing serious negative impacts on social stability and public life. In order to distinguish rumors from non-rumors, most of the existing methods are based on neural units to encode and observe the content of claims, user comments and rumor propagation patterns. However, these methods only consider the event context information in a single conversation thread, ignoring the public opinion (global contextual information) corresponding to the event in the external news environment. Be aware that users are easily distracted by opinion leaders to false facts and induced to make supportive replies on false claims. In order to address the above-mentioned limitation, we propose a Global Structural-Temporal Graph Network (GSTGN) framework. Specifically, we first construct a multi-modal global opinion graph based on the conversation threads belonging to the same event to capture the external public opinion of the target event. Then to enhance representation learning, we design a Structural-Temporal (ST) unit to encode structural and temporal features of the local conversation graph, and utilize the structural feature of the local graph to guide the learning and encoding of the global opinion graph. Experimental results on two public benchmark datasets prove that our GSTGN method achieves better results than other state-of-the-art models.

Multi-modal Rumor Detection (MRD) has emerged as a crucial research hotpot due to the continuous rise in the spread of multi-modal information on the Internet. Existing studies frequently employ traditional single-classifier models, which cannot accurately classify challenging positive samples. Moreover, the interaction of multiple modalities typically involves an additional fusion module, which results in a trade-off between the granularity of modality interaction and the complexity of the fusion modules. To address these issues, we present a model called Prompt-based Visionaware Classification and Generation (PVCG), where we use a generator module for the MRD. Notably, the encoder independently handles modality fusion more finely by including image as a soft prompt in text embeddings. Our evaluations on Fakeddit and Pheme corpus demonstrate that our PVCG outperforms the state-of-the-art baselines, showcasing its superior performance on the MRD task.

Event Factuality Identification (EFI) aims to assess the factual degree of events in texts, which is crucial and fundamental for many downstream tasks of Natural Language Processing (NLP). Document-level Event Factuality Identification (DEFI), as a branch of EFI tasks that focuses on document text, is an important task in NLP. Currently, research on DEFI is often viewed as a supervised classification task which relies on annotated information. For most datasets of DEFI, the sparsity of the data and the uneven distribution of corpora with different labels limit the research progress of the DEFI task. With the emergence of ChatGPT, it has become feasible for data augmentation by using ChatGPT, which is more accurate and fully functional than all previous tools. This precisely helps to address the problems that most datasets on DEFI have, and we can use ChatGPT to improve and expand the dataset. This paper outlines a systematic framework model, DEFI-G, which leverages Large Language Model (LLM) to process materials reported in the document, greatly expanding the original materials. Moreover, based on GAT, we change the connection method between nodes to improve their performance, resulting in improved task accuracy. The results shows that DEFI-G performs better than all previous baselines.

Cross-Document Fact Verification (CDFV) aims to retrieve related evidence from multiple documents to verify the factuality of a given claim, relying on the quality of the retrieved evidence. However, existing CDFV approaches heavily depend on specific heuristics or rule-based strategies, leveraging similarity measures of semantic or surface forms between claims and documents for evidence retrieval. To address the problem above, we propose an Evidential Graph Attention neTwork (EGAT) for CDFV. EGAT utilizes graph attention network to capture relationships between sentences, updating their representations and obtaining more expressive sentence embeddings. To acquire credible evidence, EGAT leverages golden evidence which is manually annotated and capable of verifying the factuality of the claim. Sentences in the graph that are most relevant to the gold evidence are selected as evidence sentences. To enhance the reliability of claim verification, EGAT utilizes a homogeneous network to fuse the information of the claim and evidence, which makes full use of the information provided by evidence and reduces the duplication of work in the process of claim verification. Experimental results confirm the effectiveness of EGAT in retrieving credible evidence and demonstrate improvements in achieving accurate claim verification.

With the rapid development of social media platforms and the increasing scale of the social media data, rumor spreaders are increasingly utilizing multimedia content to attract the attention and trust of news consumers. However, only relying on manual identification will consume a lot of manpower, material and financial resources. Therefore, automatic rumor detectors (i.e., using an efficient method to allow machines to automatically identify rumors) were born. However, most existing methods either only consider text features without utilizing information-rich image or social graph features, or only concatenate text features and image or social graph features, failing to fully explore the correlation between modalities, although they show good performance in rumor detection. At the same time, there are few ways to utilize all three modalities simultaneously. In this paper, we propose a novel Graph Attention Network with Cross-Modal Interaction (GANCI) method for Rumor Detection, which concurrently combines text, image and social graph features. Meanwhile, in GANCI, we designed a Feature Interaction Network to interact text, image and social graph features. Extensive experiments demonstrate the superiority of our model in comparison with the state-of-the-art baselines.

Speculation and Negation Identification focuses on the extraction of speculative and negative cues and scopes. Previous work relied on complete syntactic trees or simply fed sentences into pre-trained language models , which were confronted with poor generalization within and across datasets, and the limitations of training samples. Accordingly, we build a complete pipeline framework that firstly detects cues and then extracts scopes, and propose unified Machine Reading Comprehension paradigms for both cue detection and scope resolution on several datasets. To tackle the insufficiency of training sets and produce more useful samples with appropriate amount of lexical and syntactic knowledge, we apply data augmentation integrating lexical and syntactic features for scope resolution. Experimental results show that our model achieves higher performance than baselines on several publicly accessible corpora.

With the rapid development of social media, rumor detection on social media has become vitally crucial. Multi-modal fusion and representation play an important role in Multi-modal Rumor Detection (MRD). However, few works learn multi-modal invariant feature and discover the multi-modal class distribution with discrimination loss at the same time. In this paper, we propose a Cross-Modal Adversarial Contrastive (CMAC) fusion strategy, in which adversarial learning is used to align the latent feature distribution of text and image, and contrastive learning is used to align the feature distribution among multi-modal samples of the same category. Adversarial and contrastive learning are combined to obtain multi-modal fusion representations with modality in-variance and clear class distributions. Experimental results on two common benchmark datasets show that our approach achieves better results than other advanced models.

In the age of social media, the spread of information on the Internet transcends the geographical restrictions, and any netizen on the Internet can express views, which is the main reason that rumors on the Internet can spread rapidly. To regulate and stop the malicious spread of rumors, rumor detection automatically has become a hot field. Few previous studies consider both the temporal text information and the structural information in rumor detection, ignoring the correlation between the events. To address the above issues, this paper proposes a novel hierarchical structure based on event and topic, i.e., TEH-GCN (Topic-Event Hierarchical Graph Convolutional Networks), for rumor detection. TEH-GCN first fully learns the feature representation of rumor events at the event-level by combining the temporal and the structural information characteristics, then it uses graph network to interact the features of the rumor events in topic-level. The experimental results on the three datasets indicate that the proposed TEH-GCN can achieve better performance compared with various benchmarks.

The rapid development of social platforms has intensified the creation and spread of rumors. Hence, automatic Rumor Detection (RD) is an important and urgent task to maintain public interests and social harmony. As one of the frontier subtasks in RD, Multi-Modal Rumor Detection (MMRD) has become a new research hotspot currently. Previous methods focused on inferring clues from media content, ignoring the rich knowledge contained in texts and images. Moreover, existing methods are limited to cascade operators to encode multi-modal relationships, which cannot reflect the interactions between multiple modalities. In this paper, we propose a novel Multi-level Interaction Network (MIN), which regards entities and their relevant external knowledge as priori knowledge to provide additional features. Meanwhile, in MIN, we design a Co-Attention Network (CAN) to implement three-level interactions (i.e., the interaction between entities and image, text and external knowledge, refined text and refined image) for multi-modal fusion. Experimental results on the three public datasets (i.e., Fakeddit, Pheme and Weibo) demonstrate that our MIN model outperforms the state-of-the-arts.

With more and more messages in the form of text and image being spread on the Internet, multi-modal rumor detection has become the focus of recent research. However, most of the existing methods simply concatenate or fuse image features with text features, which can not fully explore the interaction between modalities. Meanwhile, they ignore the convergence inconsistency problem between strong and weak modalities, that is, the dominant rumor text modality may inhibit the optimization of image modality. In this paper, we investigate multi-modal rumor detection from a novel perspective, and propose a Multi-modal Graph Interactive Network with Adaptive Gradient (MGIN-AG) to solve the problem of insufficient information mining within and between modalities, and alleviate the optimization imbalance. Specifically, we first construct fine-grained graph for each rumor text or image to explicitly capture the relation between text tokens or image patches in uni-modal. Then, the cross modal interaction graph between text and image is designed to implicitly mine the text-image interaction, especially focusing on the consistency and mutual enhancement between image patches and text tokens. Furthermore, we extract the embedded text in images as an important supplement to improve the performance of the model. Finally, a strategy of dynamically adjusting the model gradient is introduced to alleviate the under optimization problem of weak modalities in the multi-modal rumor detection task. Extensive experiments demonstrate the superiority of our model in comparison with the state-of-the-art baselines.

Document-level Event Factuality Identification (DEFI) predicts the factuality of a specific event based on a document from which the event can be derived, which is a fundamental and crucial task in Natural Language Processing (NLP). However, most previous studies only considered sentence-level task and did not adopt document-level knowledge. Moreover, they modelled DEFI as a typical text classification task depending on annotated information heavily, and limited to the task-specific corpus only, which resulted in data scarcity. To tackle these issues, we propose a new framework formulating DEFI as Machine Reading Comprehension (MRC) tasks considering both Span-Extraction (Ext) and Multiple-Choice (Mch). Our model does not employ any other explicit annotated information, and utilizes Transfer Learning (TL) to extract knowledge from universal large-scale MRC corpora for cross-domain data augmentation. The empirical results on DLEFM corpus demonstrate that the proposed model outperforms several state-of-the-arts.

Document-level Event Factuality Identification (DEFI) predicts the event factuality according to the current document, and mainly depends on event-related tokens and sentences. However, previous studies relied on annotated information and did not filter irrelevant and noisy texts. Therefore, this paper proposes a novel end-to-end model, i.e., Reinforced Multi-Granularity Hierarchical Attention Network (RMHAN), which can learn information at different levels of granularity from tokens and sentences hierarchically. Moreover, with hierarchical reinforcement learning, RMHAN first selects relevant and meaningful tokens, and then selects useful sentences for document-level encoding. Experimental results on DLEF-v2 corpus show that RMHAN model outperforms several state-of-the-art baselines and achieves the best performance.

Event factuality is a description of the real situation of events in text. Event Factuality Identification (EFI) is the basic task of many related applications in the field of natural language processing. At present, most studies about EFI are carried out with the annotated event mentions, which is not applicable for practical application, and ignores the opinion of different event sources on event factuality. Moreover, previous work did not use cross-lingual information for EFI. We propose an end-to-end joint model JESF, which uses Bert to encode sentences and uses lingual feature to enrich the semantic representation of sentences, and then use BiLSTM to capture the serialized semantic features of sentences; Then, the multi-head attention is used to learn the event characteristics and identify the event mentions; After that, use multi-head attention to identify the event source; Finally, GCNs is used to capture the syntactic and semantic features, mult-head attention is used to capture the semantic features of sentences, event and event source features are integrated to identify event factuality. Especially, we use different cross-lingual related methods to learn supplementary sematic features from aligned Chinese sentences. The experimental results on FactBank show that JESF is effective and the Chinese information is helpful for English EFI, and the more effective method is to use Chinese cue as features for EFI.

The proliferation of rumors on social media has seriously affected personal life, even threatened social security and stability. Therefore, there is an urgent need to automatically detect rumors on social media. However, existing methods lack robustness because of high dimension and sparsity of natural language texts and one hundreds description ways of same events. In order to solve this issue, we propose a novel model ATSCL, which integrates adversarial training and supervised contrastive learning. We enhance ATSCL by adding adversarial perturbations in embedding layer to obtain a more robust model. At the same time, we also utilize a supervised contrastive learning objective which can shorten the distance between rumor samples, push away the distance between non-rumor samples, and further enhance the robustness of ATSCL. The experimental results on two real-word datasets Twitter15 and Twitter16 demonstrate that our method outperforms several state-of-the-art methods.

The rhetorical question is a commonly used rhetorical technique in modern Chinese. It can be divided into explicit rhetorical questions and implicit rhetorical questions according to whether it contains rhetorical cues. The implicit rhetorical questions express more emotion and are more complex in form, which has caught the attention of researchers. Most previous works relied too much on manually designed features or massive labeled data, failing to address the integration of multi-level information in sentences. In this paper, we propose a novel implicit rhetorical questions recognition framework named Hierarchical Information Fusion Graph Neural Networks (HIFGN). In particular, in order to improve the robustness of the encoder, we design a contrastive adversarial representation learning approach to map samples into the representation space. Moreover, different subgraphs of the heterogeneous graph are constructed to help the model extract profound sentence information from diverse perspectives. The experimental results on the Chinese rhetorical questions corpus show that the proposed HIFGN model achieves state-of-the-art performance on the task of implicit rhetorical questions recognition.

Due to the huge number of users and its easy access, rumors often spread widely and rapidly on social media. In order to monitor and discriminate rumor message dynamicly during propagation, automatic Rumor Detection (RD) has become an important task in NLP. This paper studies automatic event-level rumor detection on the web, which is a collection of posts in chronological order. Previous studies did not consider the connection between texts and propagation structure, which will miss useful information of temporal order or propagation structure. To address this issue, we propose a novel method Temporal Incorporating Structure Networks (TISN) to learn information from both plain text and propagation structure. Especially, we utilize transformer encoders to extract text information, and employ GCN (Graph Convolutional Network) to learn the patterns of rumor propagation. In addition, we enhance the influence of objective information by source tweet. Our method effectively achieves good performance by combining both structured and plain textual information. Experimental results on three datasets show the proposed method TISN achieves better performance than several baselines.

Sentence-level event factuality identification (SEFI) aims to identify the factuality of an event presented in a sentence. Recent neural network-based approaches have demonstrated the efficacy of the shortest dependency path, but these methods lack semantic information compared with continuous text fragments and may lead to the omission of useful information. In addition, dependency paths are relatively flat. So far, most previous work focused on English datasets, and neglected Chinese tasks. And the existing Chinese SEFI methods ignore the syntactic information. To overcome the above issues, we propose a Chinese event factuality identification model based on dependency trees. We adopt a recursive neural network-based module that fuses event selected predicates, degree words, negative words, and event triggers to capture long-range relations among them. Experimental results on the Chinese event factuality corpus show that our proposed method outperforms other baselines.

Rumors spread through the Internet, especially on Twitter, have harmed social stability and residents’ daily lives. Recently, in addition to utilizing the text features of posts for rumor detection, the structural information of rumor propagation trees has also been valued. Most rumors with salient features can be quickly locked by graph models dominated by cross entropy loss. However, these conventional models may lead to poor generalization, and lack robustness in the face of noise and adversarial rumors, or even the conversational structures that is deliberately perturbed (e.g., adding or deleting some comments). In this paper, we propose a novel Graph Adversarial Contrastive Learning (GACL) method to fight these complex cases, where the contrastive learning is introduced as part of the loss function for explicitly perceiving differences between conversational threads of the same class and different classes. At the same time, an Adversarial Feature Transformation (AFT) module is designed to produce conflicting samples for pressurizing model to mine event-invariant features. These adversarial samples are also used as hard negative samples in contrastive learning to make the model more robust and effective. Experimental results on three public benchmark datasets prove that our GACL method achieves better results than other state-of-the-art models.

We address rumor detection by learning to differentiate between the community's response to real and fake claims in microblogs. Existing state-of-the-art models are based on tree models that model conversational trees. However, in social media, a user posting a reply might be replying to the entire thread rather than to a specific user. We propose a post-level attention model (PLAN) to model long distance interactions between tweets with the multi-head attention mechanism in a transformer network. We investigated variants of this model: (1) a structure aware self-attention model (StA-PLAN) that incorporates tree structure information in the transformer network, and (2) a hierarchical token and post-level attention model (StA-HiTPLAN) that learns a sentence representation with token-level self-attention. To the best of our knowledge, we are the first to evaluate our models on two rumor detection data sets: the PHEME data set as well as the Twitter15 and Twitter16 data sets. We show that our best models outperform current state-of-the-art models for both data sets. Moreover, the attention mechanism allows us to explain rumor detection predictions at both token-level and post-level.

Event factuality identification is an important semantic task in NLP. Traditional research heavily relies on annotated texts. This paper proposes a two-step framework, first extracting essential factors related with event factuality from raw texts as the input, and then identifying the factuality of events via a Generative Adversarial Network with Auxiliary Classification (AC-GAN). The use of AC-GAN allows the model to learn more syntactic information and address the imbalance among factuality values. Experimental results on FactBank show that our method significantly outperforms several state-of-the-art baselines, particularly on events with embedded sources, speculative and negative factuality values.