Automated fact-checking (AFC) still falters on claims that are time-sensitive, entity-ambiguous, or buried beneath noisy search-engine results. We present PASS-FC, a Progressive and Adaptive Search Scheme for Fact Checking. Each atomic claim is first grounded with a precise time span and disambiguated entity descriptors. An adaptive search loop then issues structured queries, filters domains through credible-source selection, and expands queries cross-lingually; when necessary, a lightweight reflection routine restarts the loop. Experiments on six benchmark--covering general knowledge, scientific literature, real-world events, and ten languages--show that PASS-FC consistently outperforms prior systems, even those powered by larger backbone LLMs. On the multilingual X-FACT set, performance of different languages partially correlates with typological closeness to English, and forcing the model to reason in low-resource languages degrades accuracy. Ablations highlight the importance of temporal grounding and the adaptive search scheme, while detailed analysis shows that cross-lingual retrieval contributes genuinely new evidence. Code and full results will be released to facilitate further research.
Infodemics and health misinformation have significant negative impact on individuals and society, exacerbating confusion and increasing hesitancy in adopting recommended health measures. Recent advancements in generative AI, capable of producing realistic, human like text and images, have significantly accelerated the spread and expanded the reach of health misinformation, resulting in an alarming surge in its dissemination. To combat the infodemics, most existing work has focused on developing misinformation datasets from social media and fact checking platforms, but has faced limitations in topical coverage, inclusion of AI generation, and accessibility of raw content. To address these issues, we present MM Health, a large scale multimodal misinformation dataset in the health domain consisting of 34,746 news article encompassing both textual and visual information. MM Health includes human-generated multimodal information (5,776 articles) and AI generated multimodal information (28,880 articles) from various SOTA generative AI models. Additionally, We benchmarked our dataset against three tasks (reliability checks, originality checks, and fine-grained AI detection) demonstrating that existing SOTA models struggle to accurately distinguish the reliability and origin of information. Our dataset aims to support the development of misinformation detection across various health scenarios, facilitating the detection of human and machine generated content at multimodal levels.
Clarifying the research framing of NLP artefacts (e.g., models, datasets, etc.) is crucial to aligning research with practical applications. Recent studies manually analyzed NLP research across domains, showing that few papers explicitly identify key stakeholders, intended uses, or appropriate contexts. In this work, we propose to automate this analysis, developing a three-component system that infers research framings by first extracting key elements (means, ends, stakeholders), then linking them through interpretable rules and contextual reasoning. We evaluate our approach on two domains: automated fact-checking using an existing dataset, and hate speech detection for which we annotate a new dataset-achieving consistent improvements over strong LLM baselines. Finally, we apply our system to recent automated fact-checking papers and uncover three notable trends: a rise in vague or underspecified research goals, increased emphasis on scientific exploration over application, and a shift toward supporting human fact-checkers rather than pursuing full automation.
The proliferation of misinformation in digital platforms reveals the limitations of traditional detection methods, which mostly rely on static classification and fail to capture the intricate process of real-world fact-checking. Despite advancements in Large Language Models (LLMs) that enhance automated reasoning, their application to misinformation detection remains hindered by issues of logical inconsistency and superficial verification. In response, we introduce Debate-to-Detect (D2D), a novel Multi-Agent Debate (MAD) framework that reformulates misinformation detection as a structured adversarial debate. Inspired by fact-checking workflows, D2D assigns domain-specific profiles to each agent and orchestrates a five-stage debate process, including Opening Statement, Rebuttal, Free Debate, Closing Statement, and Judgment. To transcend traditional binary classification, D2D introduces a multi-dimensional evaluation mechanism that assesses each claim across five distinct dimensions: Factuality, Source Reliability, Reasoning Quality, Clarity, and Ethics. Experiments with GPT-4o on two fakenews datasets demonstrate significant improvements over baseline methods, and the case study highlight D2D's capability to iteratively refine evidence while improving decision transparency, representing a substantial advancement towards robust and interpretable misinformation detection. The code will be open-sourced in a future release.
Social media platforms have traditionally relied on internal moderation teams and partnerships with independent fact-checking organizations to identify and flag misleading content. Recently, however, platforms including X (formerly Twitter) and Meta have shifted towards community-driven content moderation by launching their own versions of crowd-sourced fact-checking -- Community Notes. If effectively scaled and governed, such crowd-checking initiatives have the potential to combat misinformation with increased scale and speed as successfully as community-driven efforts once did with spam. Nevertheless, general content moderation, especially for misinformation, is inherently more complex. Public perceptions of truth are often shaped by personal biases, political leanings, and cultural contexts, complicating consensus on what constitutes misleading content. This suggests that community efforts, while valuable, cannot replace the indispensable role of professional fact-checkers. Here we systemically examine the current approaches to misinformation detection across major platforms, explore the emerging role of community-driven moderation, and critically evaluate both the promises and challenges of crowd-checking at scale.
Determining the veracity of atomic claims is an imperative component of many recently proposed fact-checking systems. Many approaches tackle this problem by first retrieving evidence by querying a search engine and then performing classification by providing the evidence set and atomic claim to a large language model, but this process deviates from what a human would do in order to perform the task. Recent work attempted to address this issue by proposing iterative evidence retrieval, allowing for evidence to be collected several times and only when necessary. Continuing along this line of research, we propose a novel claim verification system, called EMULATE, which is designed to better emulate human actions through the use of a multi-agent framework where each agent performs a small part of the larger task, such as ranking search results according to predefined criteria or evaluating webpage content. Extensive experiments on several benchmarks show clear improvements over prior work, demonstrating the efficacy of our new multi-agent framework.
Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language models (LMs) may ignore relevant information that contradicts outdated parametric memory or be distracted by irrelevant contexts. While many context utilisation manipulation techniques (CMTs) that encourage or suppress context utilisation have recently been proposed to alleviate these issues, few have seen systematic comparison. In this paper, we develop CUB (Context Utilisation Benchmark) to help practitioners within retrieval-augmented generation (RAG) identify the best CMT for their needs. CUB allows for rigorous testing on three distinct context types, observed to capture key challenges in realistic context utilisation scenarios. With this benchmark, we evaluate seven state-of-the-art methods, representative of the main categories of CMTs, across three diverse datasets and tasks, applied to nine LMs. Our results show that most of the existing CMTs struggle to handle the full set of types of contexts that may be encountered in real-world retrieval-augmented scenarios. Moreover, we find that many CMTs display an inflated performance on simple synthesised datasets, compared to more realistic datasets with naturally occurring samples. Altogether, our results show the need for holistic tests of CMTs and the development of CMTs that can handle multiple context types.
The rapid use of large language models (LLMs) has raised critical concerns regarding the factual reliability of their outputs, especially in low-resource languages such as Urdu. Existing automated fact-checking solutions overwhelmingly focus on English, leaving a significant gap for the 200+ million Urdu speakers worldwide. In this work, we introduce UrduFactCheck, the first comprehensive, modular fact-checking framework specifically tailored for Urdu. Our system features a dynamic, multi-strategy evidence retrieval pipeline that combines monolingual and translation-based approaches to address the scarcity of high-quality Urdu evidence. We curate and release two new hand-annotated benchmarks: UrduFactBench for claim verification and UrduFactQA for evaluating LLM factuality. Extensive experiments demonstrate that UrduFactCheck, particularly its translation-augmented variants, consistently outperforms baselines and open-source alternatives on multiple metrics. We further benchmark twelve state-of-the-art (SOTA) LLMs on factual question answering in Urdu, highlighting persistent gaps between proprietary and open-source models. UrduFactCheck's code and datasets are open-sourced and publicly available at https://github.com/mbzuai-nlp/UrduFactCheck.
Automated fact-checking is a crucial task in this digital age. To verify a claim, current approaches majorly follow one of two strategies i.e. (i) relying on embedded knowledge of language models, and (ii) fine-tuning them with evidence pieces. While the former can make systems to hallucinate, the later have not been very successful till date. The primary reason behind this is that fact verification is a complex process. Language models have to parse through multiple pieces of evidence before making a prediction. Further, the evidence pieces often contradict each other. This makes the reasoning process even more complex. We proposed a simple yet effective approach where we relied on entailment and the generative ability of language models to produce ''supporting'' and ''refuting'' justifications (for the truthfulness of a claim). We trained language models based on these justifications and achieved superior results. Apart from that, we did a systematic comparison of different prompting and fine-tuning strategies, as it is currently lacking in the literature. Some of our observations are: (i) training language models with raw evidence sentences registered an improvement up to 8.20% in macro-F1, over the best performing baseline for the RAW-FC dataset, (ii) similarly, training language models with prompted claim-evidence understanding (TBE-2) registered an improvement (with a margin up to 16.39%) over the baselines for the same dataset, (iii) training language models with entailed justifications (TBE-3) outperformed the baselines by a huge margin (up to 28.57% and 44.26% for LIAR-RAW and RAW-FC, respectively). We have shared our code repository to reproduce the results.
Large Language Models (LLMs) have inherent limitations of faithfulness and factuality, commonly referred to as hallucinations. Several benchmarks have been developed that provide a test bed for factuality evaluation within the context of English-centric datasets, while relying on supplementary informative context like web links or text passages but ignoring the available structured factual resources. To this end, Knowledge Graphs (KGs) have been identified as a useful aid for hallucination mitigation, as they provide a structured way to represent the facts about entities and their relations with minimal linguistic overhead. We bridge the lack of KG paths and multilinguality for factual language modeling within the existing hallucination evaluation benchmarks and propose a KG-based multilingual, multihop benchmark called \textbf{MultiHal} framed for generative text evaluation. As part of our data collection pipeline, we mined 140k KG-paths from open-domain KGs, from which we pruned noisy KG-paths, curating a high-quality subset of 25.9k. Our baseline evaluation shows an absolute scale increase by approximately 0.12 to 0.36 points for the semantic similarity score in KG-RAG over vanilla QA across multiple languages and multiple models, demonstrating the potential of KG integration. We anticipate MultiHal will foster future research towards several graph-based hallucination mitigation and fact-checking tasks.
Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation. Existing approaches for detecting hallucination in long-form tasks either focus on limited domains or rely heavily on external fact-checking tools, which may not always be available. In this work, we systematically investigate reference-free hallucination detection in open-domain long-form responses. Our findings reveal that internal states (e.g., model's output probability and entropy) alone are insufficient for reliably (i.e., better than random guessing) distinguishing between factual and hallucinated content. To enhance detection, we explore various existing approaches, including prompting-based methods, probing, and fine-tuning, with fine-tuning proving the most effective. To further improve the accuracy, we introduce a new paradigm, named RATE-FT, that augments fine-tuning with an auxiliary task for the model to jointly learn with the main task of hallucination detection. With extensive experiments and analysis using a variety of model families & datasets, we demonstrate the effectiveness and generalizability of our method, e.g., +3% over general fine-tuning methods on LongFact.
The rapid spread of online disinformation presents a global challenge, and machine learning has been widely explored as a potential solution. However, multilingual settings and low-resource languages are often neglected in this field. To address this gap, we conducted a shared task on multilingual claim retrieval at SemEval 2025, aimed at identifying fact-checked claims that match newly encountered claims expressed in social media posts across different languages. The task includes two subtracks: (1) a monolingual track, where social posts and claims are in the same language, and (2) a crosslingual track, where social posts and claims might be in different languages. A total of 179 participants registered for the task contributing to 52 test submissions. 23 out of 31 teams have submitted their system papers. In this paper, we report the best-performing systems as well as the most common and the most effective approaches across both subtracks. This shared task, along with its dataset and participating systems, provides valuable insights into multilingual claim retrieval and automated fact-checking, supporting future research in this field.
Our fight against false information is spearheaded by fact-checkers. They investigate the veracity of claims and document their findings as fact-checking reports. With the rapid increase in the amount of false information circulating online, the use of automation in fact-checking processes aims to strengthen this ecosystem by enhancing scalability. Datasets containing fact-checked claims play a key role in developing such automated solutions. However, to the best of our knowledge, there is no fact-checking dataset at the ecosystem level, covering claims from a sufficiently long period of time and sourced from a wide range of actors reflecting the entire ecosystem that admittedly follows widely-accepted codes and principles of fact-checking. We present a new dataset FACTors, the first to fill this gap by presenting ecosystem-level data on fact-checking. It contains 118,112 claims from 117,993 fact-checking reports in English (co-)authored by 1,953 individuals and published during the period of 1995-2025 by 39 fact-checking organisations that are active signatories of the IFCN (International Fact-Checking Network) and/or EFCSN (European Fact-Checking Standards Network). It contains 7,327 overlapping claims investigated by multiple fact-checking organisations, corresponding to 2,977 unique claims. It allows to conduct new ecosystem-level studies of the fact-checkers (organisations and individuals). To demonstrate the usefulness of FACTors, we present three example applications, including a first-of-its-kind statistical analysis of the fact-checking ecosystem, examining the political inclinations of the fact-checking organisations, and attempting to assign a credibility score to each organisation based on the findings of the statistical analysis and political leanings. Our methods for constructing FACTors are generic and can be used to maintain a live dataset that can be updated dynamically.
Democratic societies need accessible, reliable information. Videos and Podcasts have established themselves as the medium of choice for civic dissemination, but also as carriers of misinformation. The emerging Science Communication Knowledge Infrastructure (SciCom KI) curating non-textual media is still fragmented and not adequately equipped to scale against the content flood. Our work sets out to support the SciCom KI with a central, collaborative platform, the SciCom Wiki, to facilitate FAIR (findable, accessible, interoperable, reusable) media representation and the fact-checking of their content, particularly for videos and podcasts. Building an open-source service system centered around Wikibase, we survey requirements from 53 stakeholders, refine these in 11 interviews, and evaluate our prototype based on these requirements with another 14 participants. To address the most requested feature, fact-checking, we developed a neurosymbolic computational fact-checking approach, converting heterogenous media into knowledge graphs. This increases machine-readability and allows comparing statements against equally represented ground-truth. Our computational fact-checking tool was iteratively evaluated through 10 expert interviews, a public user survey with 43 participants verified the necessity and usability of our tool. Overall, our findings identified several needs to systematically support the SciCom KI. The SciCom Wiki, as a FAIR digital library complementing our neurosymbolic computational fact-checking framework, was found suitable to address the raised requirements. Further, we identified that the SciCom KI is severely underdeveloped regarding FAIR knowledge and related systems facilitating its collaborative creation and curation. Our system can provide a central knowledge node, yet a collaborative effort is required to scale against the imminent (mis-)information flood.
Charts are ubiquitous as they help people understand and reason with data. Recently, various downstream tasks, such as chart question answering, chart2text, and fact-checking, have emerged. Large Vision-Language Models (LVLMs) show promise in tackling these tasks, but their evaluation is costly and time-consuming, limiting real-world deployment. While using LVLMs as judges to assess the chart comprehension capabilities of other LVLMs could streamline evaluation processes, challenges like proprietary datasets, restricted access to powerful models, and evaluation costs hinder their adoption in industrial settings. To this end, we present a comprehensive evaluation of 13 open-source LVLMs as judges for diverse chart comprehension and reasoning tasks. We design both pairwise and pointwise evaluation tasks covering criteria like factual correctness, informativeness, and relevancy. Additionally, we analyze LVLM judges based on format adherence, positional consistency, length bias, and instruction-following. We focus on cost-effective LVLMs (<10B parameters) suitable for both research and commercial use, following a standardized evaluation protocol and rubric to measure the LVLM judge's accuracy. Experimental results reveal notable variability: while some open LVLM judges achieve GPT-4-level evaluation performance (about 80% agreement with GPT-4 judgments), others struggle (below ~10% agreement). Our findings highlight that state-of-the-art open-source LVLMs can serve as cost-effective automatic evaluators for chart-related tasks, though biases such as positional preference and length bias persist.
With the wide adoption of large language models (LLMs) in information assistance, it is essential to examine their alignment with human communication styles and values. We situate this study within the context of fact-checking health information, given the critical challenge of rectifying conceptions and building trust. Recent studies have explored the potential of LLM for health communication, but style differences between LLMs and human experts and associated reader perceptions remain under-explored. In this light, our study evaluates the communication styles of LLMs, focusing on how their explanations differ from those of humans in three core components of health communication: information, sender, and receiver. We compiled a dataset of 1498 health misinformation explanations from authoritative fact-checking organizations and generated LLM responses to inaccurate health information. Drawing from health communication theory, we evaluate communication styles across three key dimensions of information linguistic features, sender persuasive strategies, and receiver value alignments. We further assessed human perceptions through a blinded evaluation with 99 participants. Our findings reveal that LLM-generated articles showed significantly lower scores in persuasive strategies, certainty expressions, and alignment with social values and moral foundations. However, human evaluation demonstrated a strong preference for LLM content, with over 60% responses favoring LLM articles for clarity, completeness, and persuasiveness. Our results suggest that LLMs' structured approach to presenting information may be more effective at engaging readers despite scoring lower on traditional measures of quality in fact-checking and health communication.
In the age of social media, the rapid spread of misinformation and rumors has led to the emergence of infodemics, where false information poses a significant threat to society. To combat this issue, we introduce TrumorGPT , a novel generative artificial intelligence solution designed for fact-checking in the health domain. TrumorGPT aims to distinguish "trumors", which are health-related rumors that turn out to be true, providing a crucial tool in differentiating between mere speculation and verified facts. This framework leverages a large language model (LLM) with few-shot learning for semantic health knowledge graph construction and semantic reasoning. TrumorGPT incorporates graph-based retrieval-augmented generation (GraphRAG) to address the hallucination issue common in LLMs and the limitations of static training data. GraphRAG involves accessing and utilizing information from regularly updated semantic health knowledge graphs that consist of the latest medical news and health information, ensuring that fact-checking by TrumorGPT is based on the most recent data. Evaluating with extensive healthcare datasets, TrumorGPT demonstrates superior performance in fact-checking for public health claims. Its ability to effectively conduct fact-checking across various platforms marks a critical step forward in the fight against health-related misinformation, enhancing trust and accuracy in the digital information age.
Democratic societies need reliable information. Misinformation in popular media such as news articles or videos threatens to impair civic discourse. Citizens are, unfortunately, not equipped to verify this content flood consumed daily at increasing rates. This work aims to semi-automatically quantify scientific accuracy of online media. By semantifying media of unknown veracity, their statements can be compared against equally processed trusted sources. We implemented a workflow using LLM-based statement extraction and knowledge graph analysis. Our neurosymbolic system was able to evidently streamline state-of-the-art veracity quantification. Evaluated via expert interviews and a user survey, the tool provides a beneficial veracity indication. This indicator, however, is unable to annotate public media at the required granularity and scale. Further work towards a FAIR (Findable, Accessible, Interoperable, Reusable) ground truth and complementary metrics are required to scientifically support civic discourse.
Human cognition is deeply intertwined with a sense of time, known as Chronoception. This sense allows us to judge how long facts remain valid and when knowledge becomes outdated. Despite progress in vision, language, and motor control, AI still struggles to reason about temporal validity. We introduce Chronocept, the first benchmark to model temporal validity as a continuous probability distribution over time. Using skew-normal curves fitted along semantically decomposed temporal axes, Chronocept captures nuanced patterns of emergence, decay, and peak relevance. It includes two datasets: Benchmark I (atomic facts) and Benchmark II (multi-sentence passages). Annotations show strong inter-annotator agreement (84% and 89%). Our baselines predict curve parameters - location, scale, and skewness - enabling interpretable, generalizable learning and outperforming classification-based approaches. Chronocept fills a foundational gap in AI's temporal reasoning, supporting applications in knowledge grounding, fact-checking, retrieval-augmented generation (RAG), and proactive agents. Code and data are publicly available.
The detection of manipulated content, a prevalent form of fake news, has been widely studied in recent years. While existing solutions have been proven effective in fact-checking and analyzing fake news based on historical events, the reliance on either intrinsic knowledge obtained during training or manually curated context hinders them from tackling zero-day manipulated content, which can only be recognized with real-time contextual information. In this work, we propose Manicod, a tool designed for detecting zero-day manipulated content. Manicod first sources contextual information about the input claim from mainstream search engines, and subsequently vectorizes the context for the large language model (LLM) through retrieval-augmented generation (RAG). The LLM-based inference can produce a "truthful" or "manipulated" decision and offer a textual explanation for the decision. To validate the effectiveness of Manicod, we also propose a dataset comprising 4270 pieces of manipulated fake news derived from 2500 recent real-world news headlines. Manicod achieves an overall F1 score of 0.856 on this dataset and outperforms existing methods by up to 1.9x in F1 score on their benchmarks on fact-checking and claim verification.