Skip to content

Explore everything

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

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 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

LLMs & generative AIDetection methods Discovering Latent Knowledge in Language Models Without SupervisionLanguage models trained with standard objectives (imitation, reward-based) can output false statements even when they internally "know" the truth. This paper proposes Contrast-Consistent Search (CCS), an unsupervised method that exploits truth's logical structure—a statement and its negation cannot both be true—to recover latent… Burns et al. · arXiv · 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

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

Psychology & interventionsFact-checking & verification The psychological drivers of misinformation belief and its resistance to correctionThis comprehensive review establishes that misinformation's power lies not in exposure but in how cognitive, social, and affective factors shape belief formation and persist even after correction. False beliefs arise from intuitive thinking, memory failures, emotional content, in-group bias, and source credibility judgments; corrections… Ecker et al. · Nature Reviews Psychology · 2022

Fact-checking & verificationDetection methods A Survey on Automated Fact-CheckingThis comprehensive survey unifies automated fact-checking research under a four-stage NLP framework: claim detection (identifying check-worthy claims), evidence retrieval (finding supporting/refuting information), verdict prediction (assigning truth labels), and justification production (explaining decisions). The authors review 25+… Guo et al. · arXiv · 2021

Psychology & interventionsPlatforms, policy & society Measuring the impact of COVID-19 vaccine misinformation on vaccination intent in the UK and USARandomized controlled trial on 8,001 respondents (4,000 UK, 4,001 USA) measuring causal impact of exposure to COVID-19 vaccine misinformation. Exposure to misinformation reduced vaccination intent by 6.2 percentage points in the UK and 6.4 in the USA relative to exposure to factual information. Loomba et al. · Nature Human Behaviour · 2021

Psychology & interventionsPlatforms, policy & society Rumors, Truths, and Reality: Political Misinformation in the Modern DayAdam Berinsky surveys a decade of research on why Americans believe political rumors despite contradictory evidence. He identifies two key mechanisms: conspiratorial thinking (a personality trait that varies across individuals) and partisanship (which structures which rumors a person is likely to endorse). Berinsky · 2021

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

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

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

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

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

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

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

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

Psychology & interventionsPlatforms, policy & society Does Media Literacy Help Identification of Fake News? Information Literacy Helps, but Other Literacies Don'tA survey of 1,299 U.S. citizens tests whether four types of media literacy—media, information, news, and digital—predict ability to identify fake news. Only information literacy (the ability to search and evaluate verified sources) significantly improves fake news identification; media, news, and digital literacies showed no significant… Jones-Jang et al. · American Behavioral Scientist · 2021

Detection methodsFact-checking & verification Generating Fact Checking ExplanationsThis paper presents the first study on automatically generating explanations for fact-checking veracity predictions. The authors show that jointly optimizing both veracity classification and explanation generation improves system performance. Atanasova et al. · arXiv · 2020

Fact-checking & verificationPlatforms, policy & society Types, Sources, and Claims of COVID-19 MisinformationSystematic analysis of 225 fact-checked COVID-19 misinformation pieces reveals that most false content reconfigures existing information (59%) rather than fabricating entirely new claims. Public authorities are cited in 39% of misinformation, yet top-down claims from politicians and celebrities account for only 20% of volume but drive… Brennen et al. · Reuters Institute for the Study of… · 2020

Spread & networksPlatforms, policy & society Assessing the risks of 'infodemics' in response to COVID-19 epidemicsAnalysis of 112+ million geolocated Twitter messages about COVID-19 (January–March 2020) across 64 languages and countries. Develops an infodemic risk index (IRI) measuring exposure to unreliable news; demonstrates that waves of unreliable information precede pandemic waves, providing early-warning signals for policy intervention. Gallotti et al. · Nature Human Behaviour · 2020

Spread & networksPlatforms, policy & society A first look at COVID-19 information and misinformation sharing on TwitterEarly-pandemic analysis of 21 million COVID-19 tweets showing Twitter conversations predict case increases by 2–5 days; identifies five prevalent myths (origin, flu comparison, heat, home remedies, vaccine) accounting for ~0.6% of tweets; finds most shared URLs point to reputable sources (CDC, WHO) rather than misinformation sites,… Singh et al. · arXiv · 2020

Psychology & interventionsDetection methods The Continued Influence of MisinformationUllrich Ecker presents research on the continued influence effect—the phenomenon that misinformation continues to shape people's reasoning and memory even after they receive corrections and understand them. He examines four social factors that shape this effect: source credibility (trustworthiness matters more than expertise),… Ecker · 2020

Datasets & evaluationSpread & networks A large-scale COVID-19 Twitter chatter dataset for open scientific research - an international collaborationBanda et al. release a massive curated corpus of 800+ million COVID-19–related tweets collected from January through November 2020, with deduplication and language diversity. The dataset adheres to FAIR principles and provides both raw tweets and metadata (terms, bigrams, trigrams, hashtags, emojis, mentions) to support research on… Banda et al. · arXiv · 2020