Skip to content
GUIDEUnderstanding fake news, misinformation & disinformation

Datasets & evaluation

Benchmarks and corpora, how they are labelled, and their known pitfalls.

151 pages Filter and search within this area
Deepfakes & multimodalDetection methods ReplayFactor: Replay-Aware Dual-Attribute Learning for Practical Speech Deepfake DetectionExisting speech deepfake detectors fail on physically replayed synthetic speech (played through a loudspeaker and re-recorded), a low-cost, practical threat to voice authentication systems. ReplayFactor addresses this by learning both source authenticity (human vs. generated) and replay presence (non-replayed vs. replayed) via SSL-based… He et al. · arXiv · 2026 Deepfakes & multimodalDetection methods UniGADD: Universal Generator-Agnostic Deepfake DetectorUniGADD proposes a two-stage supervised contrastive learning framework for detecting deepfakes from previously unseen generators. The method learns discriminative embeddings from known fake generators in stage one, then refines cluster structure via intra-cluster compactness constraints in stage two. Tomczyk et al. · arXiv · 2026 Deepfakes & multimodalDatasets & evaluation DeepfakeGenome: Toward Next-Generation Deepfake AttributionDeepfakeGenome (DFG) is a large-scale benchmark for deepfake detection and attribution covering 100 facial forgery algorithms and 2M images — 4–100× larger than prior benchmarks. The paper proposes 4 evaluation protocols using novel retrieval-based attribution metrics (mAP, Recall) instead of reject-class classification, and conducts… Wang et al. · NeurIPS 2026 · 2026 Bots & coordinated campaignsDatasets & evaluation Statistical Detectability of CoordinationThis paper formulates coordination detection as a hypothesis-testing problem on account pairs, modeling coordination as a planted submatrix. The authors derive statistical and computational detection limits, test four different null models on 26 information-operation datasets across 7 modalities, and show that multi-modal aggregation is… Iannucci et al. · arXiv · 2026 LLMs & generative AIDatasets & evaluation The uneven rise of AI-generated web contentAnalyzing 5+ million webpages from 2019–2026, this work documents that AI-generated text prevalence rose from ~2% to nearly 25% by August 2026, with uneven adoption across the web. Growth is concentrated in peripheral, poorly-connected domains rather than central platforms; English-language and .com pages show higher prevalence than .edu… Visokay et al. · arXiv · 2026 Spread & networksDatasets & evaluation Friends as Sensors: High-Sensitivity Monitoring of Misinformation and Platform Dynamics via the Friendship ParadoxThe friendship paradox—a network property where a user's friends are, on average, better connected than the user themselves—enables high-sensitivity monitoring of misinformation on Twitter/X. Comparing ~27 million tweets from randomly selected users to ~31 million from accounts those users retweet (the "sensors"), the authors find: (1)… Angermaier et al. · arXiv · 2026 LLMs & generative AIDetection methods A Large Language Model (LLM) Approach to COVID-19 Fake News DetectionThis paper evaluates seven pre-trained transformer models and LLMs for binary classification of COVID-19 tweets as real or fake using the COVID-19 English Tweets dataset (6,420 tweets). GPT-2 achieves the best performance with 96.31% accuracy and 0.96 F1-score. Arif et al. · arXiv · 2026 Platforms, policy & societyDatasets & evaluation When Platforms Pay Users to Correct Misinformation: Revenue Incentives and Governance Capacity in Weibo AnnotationsWeibo Annotations is a crowdsourced governance system that lets users add corrections and contextual information to disputed claims. In May 2025, Weibo introduced monetary rewards for approved annotations. Lin et al. · arXiv · 2026 Detection methodsDatasets & evaluation Interpretive Variation and Discourse Structure in Detecting Enthymemes in Controversial Political DiscourseEnthymemes (arguments with unstated premises or conclusions) are a persuasion technique in social media that readers may or may not recognize. This paper develops a DeBERTa-based detector on 1,482 tweets about vaccination and immigration, showing that macro-F1 reaches ~0.67 on hard labels but plateaus due to genuine human disagreement. Pastor & Oostdijk · arXiv · 2026 Platforms, policy & societyDatasets & evaluation Harm Is Behavioural, Moderation Is Lexical: How Language and Culture Decide Whom Automated Safety Systems Protect and Whom They SilenceAutomated content moderation systems recognize harm based on lexical form rather than behavioral function, creating a double inequity: dialects and minority languages face over-flagging while genuine harms (like manipulation tactics) go undetected in under-resourced languages. The paper unifies fairness literature (false positives in… Sabadin et al. · arXiv · 2026 Fact-checking & verificationPlatforms, policy & society Fact-check? True!: Tracking Verification Requests and the Absence of Truth Verdicts across Correction SystemsExamining 47,899 X/Twitter users asking Grok (X's AI assistant) whether posts are true, the authors find that ~51% of questioned posts are actually accurate, yet correction systems (Community Notes, professional fact-checkers) focus overwhelmingly on false claims. Professional fact-checkers publish true verdicts in only 8–11% of their… Wack & Warren · arXiv · 2026 LLMs & generative AIFact-checking & verification VEX-Bench: Benchmarking Verification Complexity of LLM-Generated MisinformationThis paper introduces VEX-Bench, a unified benchmark for evaluating how difficult it is to verify LLM-generated misinformation. The benchmark measures verification complexity across five dimensions: checkability (whether claims can be checked), harm significance, source credibility signals, impostor legitimacy, and verification cost. Huang et al. · NeurIPS 2026, Track on Evaluations and Datasets · 2026 Platforms, policy & societyDeepfakes & multimodal Drowning in AI Slop: How Social Media Platforms (Do Not) Label AI and Deepfake Content under EU lawThis paper conducts a legally grounded empirical audit of AI-labeling practices across Instagram, TikTok, X, and YouTube, testing how well platforms comply with EU legal obligations to label AI-generated and deepfake content. Using uploads of content generated by 10 generative AI tools, the authors find that platforms labeled only 36 of… Rijsbosch et al. · arXiv · 2026 Bots & coordinated campaignsSpread & networks Birds of a Feather Flock Together: Network-Based Detection of Coordinated Disinformation Campaigns on TelegramA graph-based methodology discovers coordinated disinformation campaigns on Telegram by analyzing message-sharing patterns rather than content, requiring only structural relationships. The authors identified 55 disinformation channels and over 86,000 identical message chains spanning multiple channels, revealing a highly synchronized… Tsagkarakis et al. · SECRYPT · 2026 Deepfakes & multimodalDatasets & evaluation VietPrism: A Large-Scale Vietnamese Speech and Deepfake Corpus with Diverse Dialects and Code-SwitchingVIETPRISM is a large-scale Vietnamese speech dataset combining 993.4 hours of bona fide utterances from 1,262 speakers with 3.1K hours of synthetically generated speech from four deepfake systems. The dataset uniquely provides transcripts, dialect annotations, speaker identities, and natural Vietnamese–English code-switching coverage. Hoang & Le · arXiv · 2026 Bots & coordinated campaignsDatasets & evaluation Setting the clock: Evaluating temporal window parameters for coordinated behavior detectionThe paper systematically evaluates how temporal window parameters (length and stride) affect detection of coordinated communities in co-repost networks. Using 14 labeled information operation datasets, the authors find that window length is a central modeling parameter: short windows (seconds to minutes) detect tight, highly synchronized… Panayiotou et al. · AIDEM Workshop, ECML-PKDD 2026 · 2026 LLMs & generative AIFact-checking & verification Calibrating Small Language Models for Claim Check-Worthiness DetectionClaim check-worthiness detection is computationally expensive when using large language models, but essential for scaling fact-checking pipelines. This paper proposes NN-PPI (Nearest Neighbor Prediction-Powered Inference), a post-hoc calibration technique that improves small LM predictions using a small labeled calibration set and… Amatya et al. · arXiv · 2026 Deepfakes & multimodalDatasets & evaluation MMMMM: A Unified Taxonomy for Investigating the Mechanisms of Multilingual MultiModal MisinformationMultimodal misinformation (images paired with misleading text) is poorly understood compared to text-only fake news, hampered by fragmented taxonomies and the complexity of annotating cross-modal relationships at scale. This work proposes a unified taxonomy of multimodal misinformation mechanisms across six orthogonal axes… Borenstein et al. · arXiv · 2026 Fact-checking & verificationDatasets & evaluation CoVer: Conflict-Aware Claim VerificationSocial media fact-checking frequently encounters conflicting evidence where different sources support or refute a claim. This paper proposes CoVer, a framework that explicitly resolves evidence-level conflicts (contradictory stances from different sources) and aggregation-level conflicts (sub-claims within complex claims yielding… Zhang et al. · arXiv · 2026 LLMs & generative AIDatasets & evaluation Counter-GEO-Bench: Evaluating Defenses Against Information-Distorting Generative Engine OptimizationAdversaries exploit Generative Engine Optimization (GEO) to craft web documents containing targeted false claims that rank highly in LLM-generated search results. This paper introduces Counter-GEO-Bench, a benchmark of 247 human-verified query-document pairs, evaluates existing guardrails (all ineffective), and proposes C-GEO Guard, a… Zheng et al. · arXiv · 2026 LLMs & generative AIDetection methods Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media postsThis paper presents BiBiR (Build-it-Break-it-Repeat), an iterative adversarial benchmarking framework for evaluating machine-generated text detectors under adversarial conditions relevant to social media. Two new datasets enable fine-tuning detectors and testing adversarial robustness. Thomas et al. · arXiv · 2026 Spread & networksDetection methods Network Information Enhances Unreliable News Domain DetectionContent-based detection of unreliable news is increasingly difficult as low-reliability sources mimic credible journalism. The authors show that network structure—how domains co-occur in social networks—can improve news-domain reliability classification. Kefler et al. · arXiv · 2026 Spread & networksDetection methods Spectral Analysis of Fake News PropagationThe paper develops a spectral view of fake news propagation by connecting graph spectra with structural properties of propagation trees. The authors derive spectral bounds capturing five key aspects of cascade structure—branching capacity, cascade scale, structural cohesion, propagation span, and diffusion dynamics—and use them as graph… Cai & Zafarani · SIAM · 2026 LLMs & generative AIDatasets & evaluation 'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic AssumptionsThe paper systematically analyzes the fragmented landscape of AI-generated text detection (AITD) task definitions in the literature and proposes a unified framework distinguishing five core notions with implicit assumptions about what constitutes "AI text." The authors introduce AITDNA, a novel dataset of 350+ texts from real human-AI… Dycke et al. · arXiv · 2026 LLMs & generative AIDatasets & evaluation Beyond Speculation: Measuring the Growing Presence of LLM-Generated Texts in Multilingual DisinformationThis empirical study provides the first measurement of LLM-generated content in real-world disinformation datasets. Analyzing the MultiClaim dataset (fact-checked social media posts), the authors document a 99% increase in machine-generated content from 2021 to 2023 (0.93% to 1.85%), correlating with ChatGPT's November 2022 release. Macko et al. · IEEE Computer · 2026 Datasets & evaluationLLMs & generative AI MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation DetectionMALINT is the first human-annotated English corpus pairing 1,600 news articles with annotations of both credibility and the malicious intentions behind disinformation. The paper evaluates 12 language models on intent classification and proposes Intent-Based Inoculation (IBI), an intent-augmented reasoning approach that improves zero-shot… Modzelewski et al. · arXiv · 2026 Deepfakes & multimodalDetection methods Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language ModelsThis paper introduces DECEPTIONDECODED, a benchmark of 12,000 image-caption pairs for evaluating multimodal misinformation detection with focus on creator intent. The authors find that state-of-the-art vision-language models struggle with intent reasoning and rely on superficial cues, motivating a framework for intent-aware multimodal… Wu et al. · ICLR 2026 · 2026 Datasets & evaluationDeepfakes & multimodal From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the WildThe paper introduces WildFakeBench, a benchmark of 10,000+ real-world micro-videos spanning diverse misinformation types (manipulation, bias, AI-generated content, out-of-context) from six social platforms. The authors propose FakeAgent, a multi-agent reasoning framework combining neural networks and large language models, which achieves… Zeng et al. · ACM International Conference · 2026 Detection methodsDatasets & evaluation A Decision-Based Heterogeneous Graph Attention Network for Multi-Class Fake News DetectionProposes DHGAT (Decision-based Heterogeneous Graph Attention Network), a semi-supervised method for six-class fake news classification on the LIAR dataset. Unlike standard GNNs that apply uniform neighborhood aggregation, DHGAT models news as heterogeneous graphs with multiple edge types derived from speaker profiles and enables each… Lakzaei et al. · arXiv · 2025 Detection methodsDatasets & evaluation Neighborhood-Order Learning Graph Attention Network for Fake News DetectionProposes NOL-GAT (Neighborhood-Order Learning Graph Attention Network), a GNN architecture that allows each node to adaptively select its optimal hop-neighborhood at each layer, bypassing the fixed L-hop limitation of conventional message-passing GNNs. Evaluated on five fake news datasets, NOL-GAT outperforms baseline GNN methods,… Lakzaei et al. · arXiv · 2025 Deepfakes & multimodalDatasets & evaluation VLDBench: Evaluating Multimodal Disinformation with Regulatory AlignmentVLDBench is the first large-scale human-verified benchmark for multimodal disinformation detection, comprising 31,339 news articles paired with images across 13 topical categories. Evaluation of 9 LLMs and 10 VLMs shows vision-language models substantially outperform text-only baselines (e.g., LLaMA-3.2-11B-Vision: 74.82% accuracy), but… Raza et al. · arXiv · 2025 Datasets & evaluationDetection methods A Guide to Misinformation Detection Data and EvaluationThis work surveys the largest collection of misinformation detection datasets to date (75 datasets from prior literature) and evaluates dataset quality across multiple dimensions. The authors assess whether datasets enable reliable veracity evaluation by analyzing keyword correlations, temporal correlations, and feasibility of claim… Thibault et al. · KDD '25 — 31st ACM SIGKDD Conference on… · 2025 Detection methodsLLMs & generative AI Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News DetectionExisting fake news detectors rely on surface-level semantic patterns (emotional language, stylistic cues) and fail when writing styles shift. This paper proposes InSIDE, which combines semantic and intent signals via heterogeneous graphs: intent models the purpose behind an article (e.g., promoting a product), while semantics capture… Wang et al. · CIKM · 2025 Detection methodsLLMs & generative AI Is Less Really More? Fake News Detection with Limited InformationSLIM (Systematically-selected Limited Information) replaces full news article text with strategically chosen subsets — extracted keywords, POS/NER sequence tags, or textual metadata — to address the computational cost and data-sparsity limitations of full-text fake news detection. Information-theoretic measures (normalized Shannon… Cao et al. · arXiv · 2025 Deepfakes & multimodalDetection methods Exposing the Deception: Uncovering More Forgery Clues for Deepfake DetectionThis paper proposes a framework for deepfake detection that extracts both local and global forgery clues by decomposing facial features into disentangled local representations. Using mutual information theory to ensure comprehensive yet non-overlapping feature extraction, the method achieves state-of-the-art results on five benchmark… Ba et al. · arXiv · 2024 LLMs & generative AIDatasets & evaluation Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of TechniquesThis comprehensive survey analyzes the integration of Large Language Models (LLMs) with Graph Representation Learning (GRL), breaking down the design space into two primary components—knowledge extractors and organizers—plus operation techniques for integration and training. The work provides a novel taxonomy for understanding how LLMs… Mao et al. · arXiv · 2024 LLMs & generative AIDatasets & evaluation The Looming Threat of Fake and LLM-generated LinkedIn Profiles: Challenges and Opportunities for Detection and PreventionLinkedIn's lack of verification enables fake accounts that harm legitimate users and the platform's integrity. This work introduces a dataset of 3600 profiles (legitimate, manually created fake, and ChatGPT-generated) and proposes SSTE, a method that detects fake profiles immediately after registration using only profile text. Ayoobi et al. · 3rd ACM Conference on Hypertext and Social Media · 2023 LLMs & generative AIDatasets & evaluation A Survey on Evaluation of Large Language ModelsThis survey provides a comprehensive review of evaluation methodologies for large language models across three dimensions: what to evaluate, where to evaluate, and how to evaluate. The paper encompasses evaluation tasks spanning natural language processing, natural language generation, robustness, ethics, bias detection, trustworthiness,… Chang et al. · Journal of the ACM · 2023 LLMs & generative AIPlatforms, policy & society Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' AlignmentThis survey provides a comprehensive framework for evaluating LLM trustworthiness across seven dimensions: reliability, safety, fairness, resistance to misuse, explainability, social norms, and robustness. The authors present a detailed taxonomy with 29 sub-categories, conduct empirical measurements on widely-used LLMs (GPT-4, ChatGPT,… Liu et al. · arXiv · 2023 Fact-checking & verificationLLMs & generative AI The Perils & Promises of Fact-checking with Large Language ModelsThis paper evaluates GPT-3.5 and GPT-4's ability to fact-check claims across English-only and multilingual datasets, showing GPT-4 substantially outperforms GPT-3.5 but both models show inconsistent accuracy when dealing with ambiguous verdicts. Critically, incorporating contextual information via Google Search significantly improves… Quelle & Bovet · arXiv · 2023 LLMs & generative AIDetection methods Adapting Fake News Detection to the Era of Large Language ModelsAs large language models proliferate and machine-generated text becomes prevalent, traditional fake news detectors trained exclusively on human-written content are increasingly unreliable. This paper evaluates fake news detectors across three hypothetical eras—human-written dominance, mixed human-machine content, and machine-generated… Su et al. · arXiv · 2023 LLMs & generative AIDetection methods The Science of Detecting LLM-Generated TextsThis survey comprehensively reviews techniques for detecting LLM-generated text, a critical problem given concerns about misinformation, academic dishonesty, and unauthorized use. The authors categorize detection approaches into black-box (API-level access) and white-box (full model access) methods, discuss watermarking strategies,… Tang et al. · arXiv · 2023 LLMs & generative AIFact-checking & verification Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-SpecificityThis comprehensive survey addresses the critical problem of factuality in large language models, examining how LLMs store and retrieve knowledge, analyzing the mechanisms through which they generate false or misleading content, and reviewing evaluation metrics and enhancement strategies. The paper distinguishes factuality issues from… Wang et al. · arXiv · 2023 LLMs & generative AIDetection methods A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future DirectionsAs LLMs become ubiquitous, detecting machine-generated text is critical for mitigating risks of misinformation, academic dishonesty, and misuse. This survey comprehensively reviews detection strategies—watermarking techniques, statistical methods, neural-based detectors, and human-assisted approaches—along with datasets, evaluation… Wu et al. · arXiv · 2023 LLMs & generative AIDatasets & evaluation How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent AdvancesThis survey reviews methods for aligning large language models with ever-changing world knowledge without retraining from scratch. The authors systematically categorize approaches as either implicit (modifying LLM parameters directly via knowledge editing or continual learning) or explicit (augmenting LLMs with external resources via… Zhang et al. · arXiv · 2023 Detection methodsLLMs & generative AI 3HAN: A Deep Neural Network for Fake News DetectionProposes 3HAN, a three-level hierarchical attention network for fake news detection that models articles as a hierarchy of words, sentences, and headlines. The model assigns differential importance weights to different parts via attention mechanisms, achieving 96.77% accuracy while providing interpretable attention visualizations showing… Singhania et al. · arXiv · 2023 Detection methodsLLMs & generative AI Linguistic-style-aware Neural Networks for Fake News DetectionHERO (Hierarchical Recursive Neural Network) detects fake news by learning the linguistic style encoded in hierarchical linguistic trees — structures that jointly capture syntactic constituency and rhetorical discourse organization from word to document. Unlike prior handcrafted approaches that extract node-level statistics (word… Zhou et al. · arXiv · 2023 Detection methodsDatasets & evaluation From Fake News to #FakeNews: Mining Direct and Indirect Relationships among Hashtags for Fake News DetectionHashtags reveal news credibility signals during propagation: fake news clusters with hashtags used primarily for misinformation, while true news uses hashtags associated with reliable content. The authors propose NewsTag, a language-independent semi-supervised algorithm that mines both direct co-occurrence and indirect relationships… Zhou et al. · ACM Conference · 2022 LLMs & generative AIFact-checking & verification Atlas: Few-shot Learning with Retrieval Augmented Language ModelsATLAS is a retrieval-augmented language model that achieves strong few-shot performance on knowledge-intensive tasks by jointly training a dense retriever with a sequence-to-sequence language model. Unlike standard language models that must memorize knowledge, ATLAS retrieves relevant documents at both pre-training and fine-tuning… Izacard et al. · arXiv · 2022 LLMs & generative AIDatasets & evaluation Discovering Language Model Behaviors with Model-Written EvaluationsRather than manually creating evaluation datasets, this work proposes using language models themselves to generate high-quality evaluations for testing diverse LM behaviors. The authors generate 154 datasets testing behaviors spanning personality, political views, ethics, and goal-seeking. Perez et al. · 2022 Bots & coordinated campaignsDatasets & evaluation Botometer 101: Social bot practicum for computational social scientistsThis tutorial introduces Botometer, a supervised machine learning classifier for detecting social bots on Twitter. The authors explain how Botometer extracts features from account profiles and tweets, describe multiple versions optimized for different use cases (including BotometerLite for large-scale analysis), and provide practical… Yang et al. · arXiv · 2022 LLMs & generative AIDetection methods Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated TextDugan et al. investigate human ability to detect boundaries where text transitions from human-written to machine-generated, a more realistic and challenging task than binary fake/real classification. They introduce the RoFT (Real or Fake Text) game platform for crowdsourced annotation and release a dataset of 21,000+ annotations across… Dugan et al. · arXiv · 2022 Datasets & evaluationDetection methods NELA-GT-2022: A Large Multi-Labelled News Dataset for The Study of Misinformation in News ArticlesPresents the fifth NELA-GT dataset release: 1.78 million news articles from 361 outlets spanning all of 2022, with source-level veracity labels from Media Bias/Fact Check and embedded tweet data. Focuses on stabilizing collection infrastructure to achieve near-complete temporal coverage, enabling robust benchmarking of fake news… Gruppi et al. · arXiv · 2022 Deepfakes & multimodalDatasets & evaluation Deepfake Detection: A Systematic Literature ReviewSystematic review of 112 deepfake detection studies (2018–2020) categorizing techniques into deep learning, machine learning, statistical, and blockchain methods. Deep learning approaches (77% of studies, primarily CNNs) significantly outperform non-deep methods, achieving ~89.7% mean accuracy. Rana et al. · IEEE Access · 2022 Spread & networksDatasets & evaluation Prevalence of Health Misinformation on Social Media: Systematic ReviewSystematic review of 69 studies examining health misinformation prevalence across social media platforms. Vaccines, drugs, and smoking are the most-studied topics; Twitter is the primary platform for misinformation about smoking and substances, while vaccines are discussed broadly across platforms. Suarez-Lledo & Alvarez-Galvez · Journal of Medical Internet Research · 2021 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 Detection methodsDatasets & evaluation Misinformation Detection on YouTube Using Video CaptionsThis work proposes using video captions as text features for classifying YouTube videos as misinformation, debunking misinformation, or neutral content. Across five conspiracy topics (vaccines, 9/11, chemtrails, moon landing, flat earth), the authors achieve 0.85–0.90 F1-score on three-class classification and 0.92–0.95 F1-score when… Jagtap et al. · arXiv · 2021 Datasets & evaluationDetection methods Assessing the Quality of the Datasets by Identifying Mislabeled SamplesDeep learning models with high capacity often memorize label noise, degrading generalization. This paper proposes AQUAVS, a supervised variational autoencoder that identifies mislabeled samples via a "noise score" computed from outliers in latent space representations. Pulastya et al. · arXiv · 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 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
See all 151 →