Online disinformation poses a global challenge, placing significant demands on fact-checkers who must verify claims efficiently to prevent the spread of false information. A major issue in this process is the redundant verification of already fact-checked claims, which increases workload and delays responses to newly emerging claims. This research introduces an approach that retrieves previously fact-checked claims, evaluates their relevance to a given input, and provides supplementary information to support fact-checkers. Our method employs large language models (LLMs) to filter irrelevant fact-checks and generate concise summaries and explanations, enabling fact-checkers to faster assess whether a claim has been verified before. In addition, we evaluate our approach through both automatic and human assessments, where humans interact with the developed tool to review its effectiveness. Our results demonstrate that LLMs are able to filter out many irrelevant fact-checks and, therefore, reduce effort and streamline the fact-checking process.
The growing spread of online misinformation has created an urgent need for scalable, reliable fact-checking solutions. Crowdsourced fact-checking - where non-experts evaluate claim veracity - offers a cost-effective alternative to expert verification, despite concerns about variability in quality and bias. Encouraged by promising results in certain contexts, major platforms such as X (formerly Twitter), Facebook, and Instagram have begun shifting from centralized moderation to decentralized, crowd-based approaches. In parallel, advances in Large Language Models (LLMs) have shown strong performance across core fact-checking tasks, including claim detection and evidence evaluation. However, their potential role in crowdsourced workflows remains unexplored. This paper investigates whether LLM-powered generative agents - autonomous entities that emulate human behavior and decision-making - can meaningfully contribute to fact-checking tasks traditionally reserved for human crowds. Using the protocol of La Barbera et al. (2024), we simulate crowds of generative agents with diverse demographic and ideological profiles. Agents retrieve evidence, assess claims along multiple quality dimensions, and issue final veracity judgments. Our results show that agent crowds outperform human crowds in truthfulness classification, exhibit higher internal consistency, and show reduced susceptibility to social and cognitive biases. Compared to humans, agents rely more systematically on informative criteria such as Accuracy, Precision, and Informativeness, suggesting a more structured decision-making process. Overall, our findings highlight the potential of generative agents as scalable, consistent, and less biased contributors to crowd-based fact-checking systems.
The rise of Internet connectivity has accelerated the spread of disinformation, threatening societal trust, decision-making, and national security. Disinformation has evolved from simple text to complex multimodal forms combining images and text, challenging existing detection methods. Traditional deep learning models struggle to capture the complexity of multimodal disinformation. Inspired by advances in AI, this study explores using Large Language Models (LLMs) for automated disinformation detection. The empirical study shows that (1) LLMs alone cannot reliably assess the truthfulness of claims; (2) providing relevant evidence significantly improves their performance; (3) however, LLMs cannot autonomously search for accurate evidence. To address this, we propose Holmes, an end-to-end framework featuring a novel evidence retrieval method that assists LLMs in collecting high-quality evidence. Our approach uses (1) LLM-powered summarization to extract key information from open sources and (2) a new algorithm and metrics to evaluate evidence quality. Holmes enables LLMs to verify claims and generate justifications effectively. Experiments show Holmes achieves 88.3% accuracy on two open-source datasets and 90.2% in real-time verification tasks. Notably, our improved evidence retrieval boosts fact-checking accuracy by 30.8% over existing methods
Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, and information retrieval. Despite its importance, current NLI systems heavily rely on supervised learning with datasets that often contain annotation artifacts and biases, limiting generalization and real-world applicability. In this work, we apply a reinforcement learning-based approach using Group Relative Policy Optimization (GRPO) for Chain-of-Thought (CoT) learning in NLI, eliminating the need for labeled rationales and enabling this type of training on more challenging datasets such as ANLI. We fine-tune 7B, 14B, and 32B language models using parameter-efficient techniques (LoRA and QLoRA), demonstrating strong performance across standard and adversarial NLI benchmarks. Our 32B AWQ-quantized model surpasses state-of-the-art results on 7 out of 11 adversarial sets$\unicode{x2013}$or on all of them considering our replication$\unicode{x2013}$within a 22GB memory footprint, showing that robust reasoning can be retained under aggressive quantization. This work provides a scalable and practical framework for building robust NLI systems without sacrificing inference quality.
Program-guided reasoning has shown promise in complex claim fact-checking by decomposing claims into function calls and executing reasoning programs. However, prior work primarily relies on few-shot in-context learning (ICL) with ad-hoc demonstrations, which limit program diversity and require manual design with substantial domain knowledge. Fundamentally, the underlying principles of effective reasoning program generation still remain underexplored, making it challenging to construct effective demonstrations. To address this, we propose BOOST, a bootstrapping-based framework for few-shot reasoning program generation. BOOST explicitly integrates claim decomposition and information-gathering strategies as structural guidance for program generation, iteratively refining bootstrapped demonstrations in a strategy-driven and data-centric manner without human intervention. This enables a seamless transition from zero-shot to few-shot strategic program-guided learning, enhancing interpretability and effectiveness. Experimental results show that BOOST outperforms prior few-shot baselines in both zero-shot and few-shot settings for complex claim verification.
Fact-checking is a potentially useful application of Large Language Models (LLMs) to combat the growing dissemination of disinformation. However, the performance of LLMs varies across geographic regions. In this paper, we evaluate the factual accuracy of open and private models across a diverse set of regions and scenarios. Using a dataset containing 600 fact-checked statements balanced across six global regions we examine three experimental setups of fact-checking a statement: (1) when just the statement is available, (2) when an LLM-based agent with Wikipedia access is utilized, and (3) as a best case scenario when a Retrieval-Augmented Generation (RAG) system provided with the official fact check is employed. Our findings reveal that regardless of the scenario and LLM used, including GPT-4, Claude Sonnet, and LLaMA, statements from the Global North perform substantially better than those from the Global South. Furthermore, this gap is broadened for the more realistic case of a Wikipedia agent-based system, highlighting that overly general knowledge bases have a limited ability to address region-specific nuances. These results underscore the urgent need for better dataset balancing and robust retrieval strategies to enhance LLM fact-checking capabilities, particularly in geographically diverse contexts.
Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. However, during multi-turn, multi-agent interactions, LLMs begin to exhibit consistent, character-like behaviors, hinting at a form of emergent lifelong learning. Despite this, existing benchmarks often fail to capture these dynamics, primarily focusing on static, open-ended evaluations. To address this gap, we introduce LIFESTATE-BENCH, a benchmark designed to assess lifelong learning in LLMs. It features two episodic datasets: Hamlet and a synthetic script collection, rich in narrative structure and character interactions. Our fact checking evaluation probes models' self-awareness, episodic memory retrieval, and relationship tracking, across both parametric and non-parametric approaches. Experiments on models like Llama3.1-8B, GPT-4-turbo, and DeepSeek R1, we demonstrate that nonparametric methods significantly outperform parametric ones in managing stateful learning. However, all models exhibit challenges with catastrophic forgetting as interactions extend, highlighting the need for further advancements in lifelong learning.
In the context of fact-checking, claims are often repeated across various platforms and in different languages, which can benefit from a process that reduces this redundancy. While retrieving previously fact-checked claims has been investigated as a solution, the growing number of unverified claims and expanding size of fact-checked databases calls for alternative, more efficient solutions. A promising solution is to group claims that discuss the same underlying facts into clusters to improve claim retrieval and validation. However, research on claim clustering is hindered by the lack of suitable datasets. To bridge this gap, we introduce \textit{MultiClaimNet}, a collection of three multilingual claim cluster datasets containing claims in 86 languages across diverse topics. Claim clusters are formed automatically from claim-matching pairs with limited manual intervention. We leverage two existing claim-matching datasets to form the smaller datasets within \textit{MultiClaimNet}. To build the larger dataset, we propose and validate an approach involving retrieval of approximate nearest neighbors to form candidate claim pairs and an automated annotation of claim similarity using large language models. This larger dataset contains 85.3K fact-checked claims written in 78 languages. We further conduct extensive experiments using various clustering techniques and sentence embedding models to establish baseline performance. Our datasets and findings provide a strong foundation for scalable claim clustering, contributing to efficient fact-checking pipelines.
Hallucinations in generative AI, particularly in Large Language Models (LLMs), pose a significant challenge to the reliability of multilingual applications. Existing benchmarks for hallucination detection focus primarily on English and a few widely spoken languages, lacking the breadth to assess inconsistencies in model performance across diverse linguistic contexts. To address this gap, we introduce Poly-FEVER, a large-scale multilingual fact verification benchmark specifically designed for evaluating hallucination detection in LLMs. Poly-FEVER comprises 77,973 labeled factual claims spanning 11 languages, sourced from FEVER, Climate-FEVER, and SciFact. It provides the first large-scale dataset tailored for analyzing hallucination patterns across languages, enabling systematic evaluation of LLMs such as ChatGPT and the LLaMA series. Our analysis reveals how topic distribution and web resource availability influence hallucination frequency, uncovering language-specific biases that impact model accuracy. By offering a multilingual benchmark for fact verification, Poly-FEVER facilitates cross-linguistic comparisons of hallucination detection and contributes to the development of more reliable, language-inclusive AI systems. The dataset is publicly available to advance research in responsible AI, fact-checking methodologies, and multilingual NLP, promoting greater transparency and robustness in LLM performance. The proposed Poly-FEVER is available at: https://huggingface.co/datasets/HanzhiZhang/Poly-FEVER.
Automated fact-checking aims to assess the truthfulness of text based on relevant evidence, yet verifying complex claims requiring multi-hop reasoning remains a significant challenge. We propose GraphCheck, a novel framework that converts claims into entity-relationship graphs for comprehensive verification. By identifying relation between explicit entities and latent entities across multiple paths, GraphCheck enhances the adaptability and robustness of verification. Furthermore, we introduce DP-GraphCheck, a two-stage variant that improves performance by incorporating direct prompting as an initial filtering step. Experiments on the HOVER and EX-FEVER datasets show that our approach outperforms existing methods, particularly in multi-hop reasoning tasks. Furthermore, our two-stage framework generalizes well to other fact-checking pipelines, demonstrating its versatility.
Automatic fact-checking aims to support professional fact-checkers by offering tools that can help speed up manual fact-checking. Yet, existing frameworks fail to address the key step of producing output suitable for broader dissemination to the general public: while human fact-checkers communicate their findings through fact-checking articles, automated systems typically produce little or no justification for their assessments. Here, we aim to bridge this gap. We argue for the need to extend the typical automatic fact-checking pipeline with automatic generation of full fact-checking articles. We first identify key desiderata for such articles through a series of interviews with experts from leading fact-checking organizations. We then develop QRAFT, an LLM-based agentic framework that mimics the writing workflow of human fact-checkers. Finally, we assess the practical usefulness of QRAFT through human evaluations with professional fact-checkers. Our evaluation shows that while QRAFT outperforms several previously proposed text-generation approaches, it lags considerably behind expert-written articles. We hope that our work will enable further research in this new and important direction.
This paper introduces AIJIM, the Artificial Intelligence Journalism Integration Model -- a novel framework for integrating real-time AI into environmental journalism. AIJIM combines Vision Transformer-based hazard detection, crowdsourced validation with 252 validators, and automated reporting within a scalable, modular architecture. A dual-layer explainability approach ensures ethical transparency through fast CAM-based visual overlays and optional LIME-based box-level interpretations. Validated in a 2024 pilot on the island of Mallorca using the NamicGreen platform, AIJIM achieved 85.4\% detection accuracy and 89.7\% agreement with expert annotations, while reducing reporting latency by 40\%. Unlike conventional approaches such as Data-Driven Journalism or AI Fact-Checking, AIJIM provides a transferable model for participatory, community-driven environmental reporting, advancing journalism, artificial intelligence, and sustainability in alignment with the UN Sustainable Development Goals and the EU AI Act.
In this paper, we evaluate the ability of Large Language Models (LLMs) to assess the veracity of claims in ''news reports'' generated by themselves or other LLMs. Our goal is to determine whether LLMs can effectively fact-check their own content, using methods similar to those used to verify claims made by humans. Our findings indicate that LLMs are more effective at assessing claims in national or international news stories than in local news stories, better at evaluating static information than dynamic information, and better at verifying true claims compared to false ones. We hypothesize that this disparity arises because the former types of claims are better represented in the training data. Additionally, we find that incorporating retrieved results from a search engine in a Retrieval-Augmented Generation (RAG) setting significantly reduces the number of claims an LLM cannot assess. However, this approach also increases the occurrence of incorrect assessments, partly due to irrelevant or low-quality search results. This diagnostic study highlights the need for future research on fact-checking machine-generated reports to prioritize improving the precision and relevance of retrieved information to better support fact-checking efforts. Furthermore, claims about dynamic events and local news may require human-in-the-loop fact-checking systems to ensure accuracy and reliability.
Identifying claims requiring verification is a critical task in automated fact-checking, especially given the proliferation of misinformation on social media platforms. Despite significant progress in the task, there remain open challenges such as dealing with multilingual and multimodal data prevalent in online discourse. Addressing the multilingual challenge, recent efforts have focused on fine-tuning pre-trained multilingual language models. While these models can handle multiple languages, their ability to effectively transfer cross-lingual knowledge for detecting claims spreading on social media remains under-explored. In this paper, we introduce \textit{EX-Claim}, an entity-aware cross-lingual claim detection model that generalizes well to handle claims written in any language. The model leverages entity information derived from named entity recognition and entity linking techniques to improve the language-level performance of both seen and unseen languages during training. Extensive experiments conducted on three datasets from different social media platforms demonstrate that our proposed model significantly outperforms the baselines, across 27 languages, and achieves the highest rate of knowledge transfer, even with limited training data.
The purpose of this study is to assess how large language models (LLMs) can be used for fact-checking and contribute to the broader debate on the use of automated means for veracity identification. To achieve this purpose, we use AI auditing methodology that systematically evaluates performance of five LLMs (ChatGPT 4, Llama 3 (70B), Llama 3.1 (405B), Claude 3.5 Sonnet, and Google Gemini) using prompts regarding a large set of statements fact-checked by professional journalists (16,513). Specifically, we use topic modeling and regression analysis to investigate which factors (e.g. topic of the prompt or the LLM type) affect evaluations of true, false, and mixed statements. Our findings reveal that while ChatGPT 4 and Google Gemini achieved higher accuracy than other models, overall performance across models remains modest. Notably, the results indicate that models are better at identifying false statements, especially on sensitive topics such as COVID-19, American political controversies, and social issues, suggesting possible guardrails that may enhance accuracy on these topics. The major implication of our findings is that there are significant challenges for using LLMs for factchecking, including significant variation in performance across different LLMs and unequal quality of outputs for specific topics which can be attributed to deficits of training data. Our research highlights the potential and limitations of LLMs in political fact-checking, suggesting potential avenues for further improvements in guardrails as well as fine-tuning.
Digital deliberation has expanded democratic participation, yet challenges remain. This includes processing information at scale, moderating discussions, fact-checking, or attracting people to participate. Recent advances in artificial intelligence (AI) offer potential solutions, but public perceptions of AI's role in deliberation remain underexplored. Beyond efficiency, democratic deliberation is about voice and recognition. If AI is integrated into deliberation, public trust, acceptance, and willingness to participate may be affected. We conducted a preregistered survey experiment with a representative sample in Germany (n=1850) to examine how information about AI-enabled deliberation influences willingness to participate and perceptions of deliberative quality. Respondents were randomly assigned to treatments that provided them information about deliberative tasks facilitated by either AI or humans. Our findings reveal a significant AI-penalty. Participants were less willing to engage in AI-facilitated deliberation and rated its quality lower than human-led formats. These effects were moderated by individual predispositions. Perceptions of AI's societal benefits and anthropomorphization of AI showed positive interaction effects on people's interest to participate in AI-enabled deliberative formats and positive quality assessments, while AI risk assessments showed negative interactions with information about AI-enabled deliberation. These results suggest AI-enabled deliberation faces substantial public skepticism, potentially even introducing a new deliberative divide. Unlike traditional participation gaps based on education or demographics, this divide is shaped by attitudes toward AI. As democratic engagement increasingly moves online, ensuring AI's role in deliberation does not discourage participation or deepen inequalities will be a key challenge for future research and policy.
Fact-checking plays a crucial role in combating misinformation. Existing methods using large language models (LLMs) for claim decomposition face two key limitations: (1) insufficient decomposition, introducing unnecessary complexity to the verification process, and (2) ambiguity of mentions, leading to incorrect verification results. To address these challenges, we suggest introducing a claim graph consisting of triplets to address the insufficient decomposition problem and reduce mention ambiguity through graph structure. Based on this core idea, we propose a graph-based framework, GraphFC, for fact-checking. The framework features three key components: graph construction, which builds both claim and evidence graphs; graph-guided planning, which prioritizes the triplet verification order; and graph-guided checking, which verifies the triples one by one between claim and evidence graphs. Extensive experiments show that GraphFC enables fine-grained decomposition while resolving referential ambiguities through relational constraints, achieving state-of-the-art performance across three datasets.
The increasing prevalence of online misinformation has heightened the demand for automated fact-checking solutions. Large Language Models (LLMs) have emerged as potential tools for assisting in this task, but their effectiveness remains uncertain. This study evaluates the fact-checking capabilities of various open-source LLMs, focusing on their ability to assess claims with different levels of contextual information. We conduct three key experiments: (1) evaluating whether LLMs can identify the semantic relationship between a claim and a fact-checking article, (2) assessing models' accuracy in verifying claims when given a related fact-checking article, and (3) testing LLMs' fact-checking abilities when leveraging data from external knowledge sources such as Google and Wikipedia. Our results indicate that LLMs perform well in identifying claim-article connections and verifying fact-checked stories but struggle with confirming factual news, where they are outperformed by traditional fine-tuned models such as RoBERTa. Additionally, the introduction of external knowledge does not significantly enhance LLMs' performance, calling for more tailored approaches. Our findings highlight both the potential and limitations of LLMs in automated fact-checking, emphasizing the need for further refinements before they can reliably replace human fact-checkers.
Online misinformation remains a critical challenge, and fact-checkers increasingly rely on embedding-based methods to retrieve relevant fact-checks. Yet, when debunked claims reappear in edited forms, the performance of these methods is unclear. In this work, we introduce a taxonomy of six common real-world misinformation edits and propose a perturbation framework that generates valid, natural claim variations. Our multi-stage retrieval evaluation reveals that standard embedding models struggle with user-introduced edits, while LLM-distilled embeddings offer improved robustness at a higher computational cost. Although a strong reranker helps mitigate some issues, it cannot fully compensate for first-stage retrieval gaps. Addressing these retrieval gaps, our train- and inference-time mitigation approaches enhance in-domain robustness by up to 17 percentage points and boost out-of-domain generalization by 10 percentage points over baseline models. Overall, our findings provide practical improvements to claim-matching systems, enabling more reliable fact-checking of evolving misinformation.
The proliferation of misinformation on social media has raised significant societal concerns, necessitating robust detection mechanisms. Large Language Models such as GPT-4 and LLaMA2 have been envisioned as possible tools for detecting misinformation based on their advanced natural language understanding and reasoning capabilities. This paper conducts a comparison of LLM-based approaches to detecting misinformation between text-based, multimodal, and agentic approaches. We evaluate the effectiveness of fine-tuned models, zero-shot learning, and systematic fact-checking mechanisms in detecting misinformation across different topic domains like public health, politics, and finance. We also discuss scalability, generalizability, and explainability of the models and recognize key challenges such as hallucination, adversarial attacks on misinformation, and computational resources. Our findings point towards the importance of hybrid approaches that pair structured verification protocols with adaptive learning techniques to enhance detection accuracy and explainability. The paper closes by suggesting potential avenues of future work, including real-time tracking of misinformation, federated learning, and cross-platform detection models.