Skip to content
GUIDEUnderstanding fake news, misinformation & disinformation

Explore papers

Filter by research area, year and venue. Every filter is in the address bar, so you can share a view as a link.

369 results
CardsList
Detection methodsLLMs & generative AI A Heuristic-driven Uncertainty based Ensemble Framework for Fake News Detection in Tweets and News ArticlesAn ensemble-based fake news detection system combining multiple pre-trained language models (BERT, RoBERTa, XLNet, DeBERTa, ERNIE 2.0, ELECTRA) with a Statistical Feature Fusion Network (SFFN) and heuristic post-processing. The framework incorporates Monte Carlo Dropout for uncertainty estimation and leverages metadata features (URL… Das et al. · arXiv · 2021 LLMs & generative AIDeepfakes & multimodal On the Opportunities and Risks of Foundation ModelsA comprehensive 214-page report analyzing foundation models—large neural networks trained on broad data that can be adapted to diverse downstream tasks (BERT, GPT-3, DALL-E). The report maps capabilities across language, vision, and reasoning; applications in healthcare, law, and education; and societal risks including misuse (generating… Bommasani et al. · arXiv · 2021 LLMs & generative AI A General Language Assistant as a Laboratory for AlignmentAnthropic builds an interactive evaluation framework for measuring large language model alignment using three criteria: helpfulness, honesty, and harmlessness (HHH). By comparing prompting, imitation learning, binary discrimination, and ranked preference modeling approaches, the authors find that ranked preference models scale better… Askell et al. · arXiv · 2021 Spread & networksDatasets & evaluation A Survey of Information Cascade Analysis: Models, Predictions, and Recent AdvancesThis comprehensive survey systematizes research on predicting information cascade growth and structure across social networks, covering feature-based models, generative models, and deep learning approaches. It provides a taxonomy of prediction methods across temporal, structural, user/item, and content features; evaluation metrics and… Zhou et al. · ACM Computing Surveys · 2021 Detection methodsLLMs & generative AI Hierarchical Multi-head Attentive Network for Evidence-aware Fake News DetectionThe paper proposes MAC, a hierarchical multi-head attention network that jointly learns word-level and document-level attention for fact-checking textual claims against evidence from external sources. Multi-head attention mechanisms capture different semantic aspects of claims and evidence documents, enabling the model to focus on… Vo & Lee · arXiv · 2021 Spread & networksPlatforms, policy & society Prevalence of Health Misinformation on Social Media: Systematic ReviewThis systematic review of 69 studies characterizes health misinformation topics and their prevalence across social media platforms. Health misinformation was most prevalent on Twitter regarding smoking and drugs; vaccines, noncommunicable diseases, and pandemics were also common topics. Suarez-Lledo & Alvarez-Galvez · Journal of Medical Internet Research · 2021 Spread & networksPsychology & interventions The Gospel According to Q: Understanding the QAnon Conspiracy from the Perspective of Canonical InformationThis paper systematically studies the QAnon conspiracy theory by collecting and analyzing 4,961 unique Q drops from six aggregation sites. The authors find that aggregation sites show poor agreement on what constitutes a canonical Q drop, that Q drops are incoherent and low-quality relative to other social media platforms, and that… Papasavva et al. · 16th International AAAI Conference on Web and… · 2021 Detection methodsDatasets & evaluation MDFEND: Multi-domain Fake News DetectionMost fake news detection methods focus on single-domain data, which leads to poor performance across different domains due to domain shift (varying word usage and propagation patterns). This paper introduces Weibo21, the first multi-domain fake news dataset from a single platform with 9 domains, and proposes MDFEND, a model using… Nan et al. · CIKM '21: The 30th ACM International… · 2021 Fact-checking & verificationDatasets & evaluation A Survey on Predicting the Factuality and the Bias of News MediaSurvey of media-level profiling methods for predicting news outlet factuality and political bias. Rather than checking individual claims or articles, the approach profiles entire news sources to enable early detection of unreliable content at publication time. Nakov et al. · arXiv · 2021 Platforms, policy & societyBots & coordinated campaigns The Threat of Offensive AI to OrganizationsA comprehensive survey identifying 33 offensive AI capabilities that adversaries can use to attack organizations, organized into seven categories: automation, campaign resilience, credential theft, exploit development, information gathering, social engineering, and stealth. Through a user study with 22 experts from academia and industry,… Mirsky et al. · ACM Computing Surveys · 2021 Detection methodsDatasets & evaluation DEAP-FAKED: Knowledge Graph based Approach for Fake News DetectionDEAP-FAKED combines a biLSTM news encoder with knowledge graph embeddings to detect fake news using only article titles. The approach extracts named entities from titles, maps them to Wikidata using named entity disambiguation, and embeds them via ComplEx. Mayank et al. · IEEE/ACM International Conference on Advances… · 2021 LLMs & generative AIDatasets & evaluation TruthfulQA: Measuring How Models Mimic Human FalsehoodsIntroduces TruthfulQA, a benchmark of 817 questions across 38 categories designed to measure whether language models generate truthful answers. Tests GPT-3, GPT-Neo/J, GPT-2, and T5-based models, finding that larger models are less truthful—an inverse scaling phenomenon where the best model (GPT-3-175B) achieves only 58% truthfulness… Lin et al. · arXiv · 2021 Detection methodsLLMs & generative AI FakeBERT: Fake News Detection in Social Media with a BERT-based Deep Learning ApproachFakeBERT combines BERT (Bidirectional Encoder Representations from Transformers) with parallel 1D convolutional neural networks to detect fake news on social media. The model captures semantic and long-distance dependencies in text, achieving 98.90% accuracy on the real-world fake news dataset and substantially outperforming CNN and LSTM… Kaliyar et al. · Multimedia Tools and Applications · 2021 Detection methodsLLMs & generative AI Towards Fine-Grained Reasoning for Fake News DetectionThe paper proposes FinerFact, a framework for fake news detection that models reasoning at the claim-evidence level rather than the document level. It constructs claim-evidence graphs and uses mutual-reinforcement-based ranking to identify salient evidence, then applies a bi-channel kernel graph network to reason over evidence groups. Jin et al. · ACL · 2021 Fact-checking & verificationDatasets & evaluation A Survey on Stance Detection for Mis- and Disinformation IdentificationComprehensive survey of stance detection for misinformation and disinformation. Stance detection—determining whether a text supports, denies, questions, or merely comments on a claim—plays dual roles: as a standalone fact-checking tool and as a component in broader verification pipelines. Hardalov et al. · arXiv · 2021 LLMs & generative AIPlatforms, policy & society Truthful AI: Developing and Governing AI That Does Not LieAs AI systems become more capable and widely deployed, strategic falsehoods—"lies" that AI generates to achieve specified objectives—pose increasing risks. This paper proposes a framework of truthfulness standards for AI systems, governance mechanisms to enforce them (including certification bodies and verification procedures), and… Evans et al. · arXiv · 2021 Detection methodsLLMs & generative AI KAN: Knowledge-aware Attention Network for Fake News DetectionMost fake news detection models rely on textual features and social context but ignore knowledge-level relationships among entities in news. This paper proposes KAN, which extracts entity mentions from news, aligns them with knowledge graphs (Wikidata), and uses two attention mechanisms (N-E and N-E2C) to measure entity and… Dun et al. · AAAI 2021 · 2021 Detection methodsDatasets & evaluation Cross-lingual COVID-19 Fake News DetectionThe paper addresses COVID-19 misinformation in low-resource languages by proposing CrossFake, a cross-lingual fake news detector trained on English COVID-19 news and applied to Chinese news via machine translation. The method slices long news texts into sub-text groups before BERT encoding to preserve fact-related information. Du et al. · arXiv · 2021 Detection methodsSpread & networks User Preference-aware Fake News DetectionProposes UPFD, which detects fake news by jointly modeling user endogenous preferences (from historical posts) and exogenous context (news propagation graphs) via GNNs. Shows confirmation bias drives news sharing decisions, and historical user behavior provides complementary signals to improve detection over content-only and graph-only… Dou et al. · SIGIR 2021 · 2021 LLMs & generative AIDatasets & evaluation All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated TextHuman evaluators cannot reliably distinguish machine-generated text from human-written text without training, focusing instead on superficial features like grammar and style. Three training approaches (instructions, examples, and comparisons) improve evaluator accuracy modestly, with example-based training showing the most improvement… Clark et al. · arXiv · 2021 Spread & networksDetection methods Causal Understanding of Fake News Dissemination on Social MediaThe paper addresses the fundamental causal question: what user attributes cause susceptibility to share fake news? Rather than observing correlations, the authors use inverse propensity scoring (IPS) to learn unbiased embeddings of fake news sharing behavior, treating these embeddings as confounders in a causal model. Cheng et al. · ACM SIGKDD Conference on Knowledge Discovery… · 2021 Deepfakes & multimodalDetection methods A Survey on Multimodal Disinformation DetectionComprehensive survey of multimodal disinformation detection covering text, images, speech, video, network structure, and temporal information. Distinguishes factuality (whether content is false) from harmfulness (whether false content intends to harm), systematically reviews ~140 papers across different modalities and detection… Alam et al. · arXiv · 2021 Detection methodsDeepfakes & multimodal Embracing Domain Differences in Fake News: Cross-domain Fake News Detection using Multimodal DataMost fake news detection models are trained on a single domain (e.g., politics) and fail when tested on others (e.g., entertainment, COVID-19). This paper proposes a multimodal framework that leverages both domain-specific and cross-domain knowledge to detect fake news across different domains. Silva et al. · AAAI 2021 · 2021 Psychology & interventionsSpread & networks News literacy, social media behaviors, and skepticism toward information on social mediaA national survey of 788 Americans examines how news literacy relates to what people see and share on social media, and whether it predicts skepticism toward information shared in these spaces. The key finding: people with higher news literacy see and post less political content on social media, but when they do engage, they're… Vraga & Tully · Information, Communication & Society · 2021