In this paper, we explore the problem of Claim Extraction using one-to-many text generation methods, comparing LLMs, small summarization models finetuned for the task, and a previous NER-centric baseline QACG. As the current publications on Claim Extraction, Fact Extraction, Claim Generation and Check-worthy Claim Detection are quite scattered in their means and terminology, we compile their common objectives, releasing the FEVERFact dataset, with 17K atomic factual claims extracted from 4K contextualised Wikipedia sentences, adapted from the original FEVER. We compile the known objectives into an Evaluation framework of: Atomicity, Fluency, Decontextualization, Faithfulness checked for each generated claim separately, and Focus and Coverage measured against the full set of predicted claims for a single input. For each metric, we implement a scale using a reduction to an already-explored NLP task. We validate our metrics against human grading of generic claims, to see that the model ranking on $F_{fact}$, our hardest metric, did not change and the evaluation framework approximates human grading very closely in terms of $F_1$ and RMSE.
Free-text explanations are expressive and easy to understand, but many datasets lack annotated explanation data, making it challenging to train models for explainable predictions. To address this, we investigate how to use existing explanation datasets for self-rationalization and evaluate models' out-of-distribution (OOD) performance. We fine-tune T5-Large and OLMo-7B models and assess the impact of fine-tuning data quality, the number of fine-tuning samples, and few-shot selection methods. The models are evaluated on 19 diverse OOD datasets across three tasks: natural language inference (NLI), fact-checking, and hallucination detection in abstractive summarization. For the generated explanation evaluation, we conduct a human study on 13 selected models and study its correlation with the Acceptability score (T5-11B) and three other LLM-based reference-free metrics. Human evaluation shows that the Acceptability score correlates most strongly with human judgments, demonstrating its effectiveness in evaluating free-text explanations. Our findings reveal: 1) few annotated examples effectively adapt models for OOD explanation generation; 2) compared to sample selection strategies, fine-tuning data source has a larger impact on OOD performance; and 3) models with higher label prediction accuracy tend to produce better explanations, as reflected by higher Acceptability scores.
Large Language Models (LLMs) are increasingly used to assess news credibility, yet little is known about how they make these judgments. While prior research has examined political bias in LLM outputs or their potential for automated fact-checking, their internal evaluation processes remain largely unexamined. Understanding how LLMs assess credibility provides insights into AI behavior and how credibility is structured and applied in large-scale language models. This study benchmarks the reliability and political classifications of state-of-the-art LLMs - Gemini 1.5 Flash (Google), GPT-4o mini (OpenAI), and LLaMA 3.1 (Meta) - against structured, expert-driven rating systems such as NewsGuard and Media Bias Fact Check. Beyond assessing classification performance, we analyze the linguistic markers that shape LLM decisions, identifying which words and concepts drive their evaluations. We uncover patterns in how LLMs associate credibility with specific linguistic features by examining keyword frequency, contextual determinants, and rank distributions. Beyond static classification, we introduce a framework in which LLMs refine their credibility assessments by retrieving external information, querying other models, and adapting their responses. This allows us to investigate whether their assessments reflect structured reasoning or rely primarily on prior learned associations.
Large language models (LLMs) have shown impressive capabilities in natural language processing tasks, including dialogue generation. This research aims to conduct a novel comparative analysis of two prominent techniques, fine-tuning with LoRA (Low-Rank Adaptation) and the Retrieval-Augmented Generation (RAG) framework, in the context of doctor-patient chat conversations with multiple datasets of mixed medical domains. The analysis involves three state-of-the-art models: Llama-2, GPT, and the LSTM model. Employing real-world doctor-patient dialogues, we comprehensively evaluate the performance of models, assessing key metrics such as language quality (perplexity, BLEU score), factual accuracy (fact-checking against medical knowledge bases), adherence to medical guidelines, and overall human judgments (coherence, empathy, safety). The findings provide insights into the strengths and limitations of each approach, shedding light on their suitability for healthcare applications. Furthermore, the research investigates the robustness of the models in handling diverse patient queries, ranging from general health inquiries to specific medical conditions. The impact of domain-specific knowledge integration is also explored, highlighting the potential for enhancing LLM performance through targeted data augmentation and retrieval strategies.
Evaluating the truthfulness of online content is critical for combating misinformation. This study examines the efficiency and effectiveness of crowdsourced truthfulness assessments through a comparative analysis of two approaches: one involving full-length webpages as evidence for each claim, and another using summaries for each evidence document generated with a large language model. Using an A/B testing setting, we engage a diverse pool of participants tasked with evaluating the truthfulness of statements under these conditions. Our analysis explores both the quality of assessments and the behavioral patterns of participants. The results reveal that relying on summarized evidence offers comparable accuracy and error metrics to the Standard modality while significantly improving efficiency. Workers in the Summary setting complete a significantly higher number of assessments, reducing task duration and costs. Additionally, the Summary modality maximizes internal agreement and maintains consistent reliance on and perceived usefulness of evidence, demonstrating its potential to streamline large-scale truthfulness evaluations.
We propose a novel paradigm for automatic fact-checking that leverages frame semantics to enhance the structured understanding of claims, addressing the challenges posed by misinformation in today's information ecosystem. To support this approach, we introduce a pilot dataset of real-world claims extracted from PolitiFact, specifically annotated for large-scale structured data. This dataset underpins two case studies: the first investigates voting-related claims using the Vote semantic frame, while the second explores various semantic frames and data sources from the Organisation for Economic Co-operation and Development (OECD). Our findings demonstrate the effectiveness of frame semantics in improving evidence retrieval, indicating a meaningful advancement in automatic fact-checking capabilities. Finally, we conducted a survey of frames evoked in fact-checked claims, identifying high-impact frames to guide future research.
In recent years, the rapid development of AI systems has brought about the benefits of intelligent services but also concerns about security and reliability. By fostering appropriate user reliance on an AI system, both complementary team performance and reduced human workload can be achieved. Previous empirical studies have extensively analyzed the impact of factors ranging from task, system, and human behavior on user trust and appropriate reliance in the context of one-step decision making. However, user reliance on AI systems in tasks with complex semantics that require multi-step workflows remains under-explored. Inspired by recent work on task decomposition with large language models, we propose to investigate the impact of a novel Multi-Step Transparent (MST) decision workflow on user reliance behaviors. We conducted an empirical study (N = 233) of AI-assisted decision making in composite fact-checking tasks (i.e., fact-checking tasks that entail multiple sub-fact verification steps). Our findings demonstrate that human-AI collaboration with an MST decision workflow can outperform one-step collaboration in specific contexts (e.g., when advice from an AI system is misleading). Further analysis of the appropriate reliance at fine-grained levels indicates that an MST decision workflow can be effective when users demonstrate a relatively high consideration of the intermediate steps. Our work highlights that there is no one-size-fits-all decision workflow that can help obtain optimal human-AI collaboration. Our insights help deepen the understanding of the role of decision workflows in facilitating appropriate reliance. We synthesize important implications for designing effective means to facilitate appropriate reliance on AI systems in composite tasks, positioning opportunities for the human-centered AI and broader HCI communities.
The claim matching (CM) task can benefit an automated fact-checking pipeline by putting together claims that can be resolved with the same fact-check. In this work, we are the first to explore zero-shot and few-shot learning approaches to the task. We consider CM as a binary classification task and experiment with a set of instruction-following large language models (GPT-3.5-turbo, Gemini-1.5-flash, Mistral-7B-Instruct, and Llama-3-8B-Instruct), investigating prompt templates. We introduce a new CM dataset, ClaimMatch, which will be released upon acceptance. We put LLMs to the test in the CM task and find that it can be tackled by leveraging more mature yet similar tasks such as natural language inference or paraphrase detection. We also propose a pipeline for CM, which we evaluate on texts of different lengths.
The rapid spread of fake news presents a significant global challenge, particularly in low-resource languages like Bangla, which lack adequate datasets and detection tools. Although manual fact-checking is accurate, it is expensive and slow to prevent the dissemination of fake news. Addressing this gap, we introduce BanFakeNews-2.0, a robust dataset to enhance Bangla fake news detection. This version includes 11,700 additional, meticulously curated fake news articles validated from credible sources, creating a proportional dataset of 47,000 authentic and 13,000 fake news items across 13 categories. In addition, we created a manually curated independent test set of 460 fake and 540 authentic news items for rigorous evaluation. We invest efforts in collecting fake news from credible sources and manually verified while preserving the linguistic richness. We develop a benchmark system utilizing transformer-based architectures, including fine-tuned Bidirectional Encoder Representations from Transformers variants (F1-87\%) and Large Language Models with Quantized Low-Rank Approximation (F1-89\%), that significantly outperforms traditional methods. BanFakeNews-2.0 offers a valuable resource to advance research and application in fake news detection for low-resourced languages. We publicly release our dataset and model on Github to foster research in this direction.
Understanding how misleading and outright false information enters news ecosystems remains a difficult challenge that requires tracking how narratives spread across thousands of fringe and mainstream news websites. To do this, we introduce a system that utilizes encoder-based large language models and zero-shot stance detection to scalably identify and track news narratives and their attitudes across over 4,000 factually unreliable, mixed-reliability, and factually reliable English-language news websites. Running our system over an 18 month period, we track the spread of 146K news stories. Using network-based interference via the NETINF algorithm, we show that the paths of news narratives and the stances of websites toward particular entities can be used to uncover slanted propaganda networks (e.g., anti-vaccine and anti-Ukraine) and to identify the most influential websites in spreading these attitudes in the broader news ecosystem. We hope that increased visibility into our distributed news ecosystem can help with the reporting and fact-checking of propaganda and disinformation.
Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited by the traditional RAG design. To address these challenges, we introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources. The memory is refreshed based on online fact-checking and retrieval feedback, allowing EWE to rectify false claims during the generation process and ensure more accurate and reliable outputs. Our experiments demonstrate that Ewe outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 10 points absolute without sacrificing the helpfulness of the responses. Further analysis reveals that the design of rules for memory updates, configurations of memory units, and the quality of the retrieval datastore are crucial factors for influencing model performance.
The pervasive influence of social media during the COVID-19 pandemic has been a double-edged sword, enhancing communication while simultaneously propagating misinformation. This \textit{Digital Infodemic} has highlighted the urgent need for automated tools capable of discerning and disseminating factual content. This study evaluates the efficacy of Large Language Models (LLMs) as innovative solutions for mitigating misinformation on platforms like Twitter. LLMs, such as OpenAI's GPT and Meta's LLaMA, offer a pre-trained, adaptable approach that bypasses the extensive training and overfitting issues associated with traditional machine learning models. We assess the performance of LLMs in detecting and classifying COVID-19-related scientific claims, thus facilitating informed decision-making. Our findings indicate that LLMs have significant potential as automated fact-checking tools, though research in this domain is nascent and further exploration is required. We present a comparative analysis of LLMs' performance using a specialized dataset and propose a framework for their application in public health communication.
The rapid spread of information in the digital age highlights the critical need for effective fact-checking tools, particularly for languages with limited resources, such as Vietnamese. In response to this challenge, we introduce ViFactCheck, the first publicly available benchmark dataset designed specifically for Vietnamese fact-checking across multiple online news domains. This dataset contains 7,232 human-annotated pairs of claim-evidence combinations sourced from reputable Vietnamese online news, covering 12 diverse topics. It has been subjected to a meticulous annotation process to ensure high quality and reliability, achieving a Fleiss Kappa inter-annotator agreement score of 0.83. Our evaluation leverages state-of-the-art pre-trained and large language models, employing fine-tuning and prompting techniques to assess performance. Notably, the Gemma model demonstrated superior effectiveness, with an impressive macro F1 score of 89.90%, thereby establishing a new standard for fact-checking benchmarks. This result highlights the robust capabilities of Gemma in accurately identifying and verifying facts in Vietnamese. To further promote advances in fact-checking technology and improve the reliability of digital media, we have made the ViFactCheck dataset, model checkpoints, fact-checking pipelines, and source code freely available on GitHub. This initiative aims to inspire further research and enhance the accuracy of information in low-resource languages.
In recent years, large language models (LLMs) have demonstrated significant success in performing varied natural language tasks such as language translation, question-answering, summarizing, fact-checking, etc. Despite LLMs' impressive ability to generate human-like texts, LLMs are infamous for their inconsistent responses -- a meaning-preserving change in the input query results in an inconsistent response and attributes to vulnerabilities of LLMs such as hallucination, jailbreaking, etc. Consequently, existing research focuses on simple paraphrasing-based consistency assessment of LLMs, and ignores complex queries that necessitates an even better understanding of logical reasoning by an LLM. Our work therefore addresses the logical inconsistency of LLMs under complex logical queries with primitive logical operators, e.g., negation, conjunction, and disjunction. As a test bed, we consider retrieval-augmented LLMs on a fact-checking task involving propositional logic queries from real-world knowledge graphs (KGs). Our contributions are three-fold. Benchmark: We introduce three logical fact-checking datasets over KGs for community development towards logically consistent LLMs. Assessment: We propose consistency measures of LLMs on propositional logic queries as input and demonstrate that existing LLMs lack logical consistency, specially on complex queries. Improvement: We employ supervised fine-tuning to improve the logical consistency of LLMs on the complex fact-checking task with KG contexts.
Natural Language Processing and Generation systems have recently shown the potential to complement and streamline the costly and time-consuming job of professional fact-checkers. In this work, we lift several constraints of current state-of-the-art pipelines for automated fact-checking based on the Retrieval-Augmented Generation (RAG) paradigm. Our goal is to benchmark, under more realistic scenarios, RAG-based methods for the generation of verdicts - i.e., short texts discussing the veracity of a claim - evaluating them on stylistically complex claims and heterogeneous, yet reliable, knowledge bases. Our findings show a complex landscape, where, for example, LLM-based retrievers outperform other retrieval techniques, though they still struggle with heterogeneous knowledge bases; larger models excel in verdict faithfulness, while smaller models provide better context adherence, with human evaluations favouring zero-shot and one-shot approaches for informativeness, and fine-tuned models for emotional alignment.
The proliferation of disinformation presents a growing threat to societal trust and democracy, necessitating robust and scalable Fact-Checking systems. In this work, we present Dynamic Evidence-based FAct-checking with Multimodal Experts (DEFAME), a modular, zero-shot MLLM pipeline for open-domain, text-image claim verification. DEFAME frames the problem of fact-checking as a six-stage process, dynamically deciding about the usage of external tools for the retrieval of textual and visual evidence. In addition to the claim's veracity, DEFAME returns a justification accompanied by a comprehensive, multimodal fact-checking report. While most alternatives either focus on sub-tasks of fact-checking, lack explainability or are limited to text-only inputs, DEFAME solves the problem of fact-checking end-to-end, including claims with images or those that require visual evidence. Evaluation on the popular benchmarks VERITE, AVeriTeC, and MOCHEG shows that DEFAME surpasses all previous methods, establishing it as the new state-of-the-art fact-checking system.
In fact-checking, structure and phrasing of claims critically influence a model's ability to predict verdicts accurately. Social media content in particular rarely serves as optimal input for verification systems, which necessitates pre-processing to extract the claim from noisy context before fact checking. Prior work suggests extracting a claim representation that humans find to be checkworthy and verifiable. This has two limitations: (1) the format may not be optimal for a fact-checking model, and (2), it requires annotated data to learn the extraction task from. We address both issues and propose a method to extract claims that is not reliant on labeled training data. Instead, our self-adaptive approach only requires a black-box fact checking model and a generative language model (LM). Given a tweet, we iteratively optimize the LM to generate a claim paraphrase that increases the performance of a fact checking model. By learning from preference pairs, we align the LM to the fact checker using direct preference optimization. We show that this novel setup extracts a claim paraphrase that is more verifiable than their original social media formulations, and is on par with competitive baselines. For refuted claims, our method consistently outperforms all baselines.
Given the massive volume of potentially false claims circulating online, claim prioritization is essential in allocating limited human resources available for fact-checking. In this study, we perceive claim prioritization as an information retrieval (IR) task: just as multidimensional IR relevance, with many factors influencing which search results a user deems relevant, checkworthiness is also multi-faceted, subjective, and even personal, with many factors influencing how fact-checkers triage and select which claims to check. Our study investigated both the multidimensional nature of checkworthiness and effective tool support to assist fact-checkers in claim prioritization. Methodologically, we pursued Research through Design combined with mixed-method evaluation. Specifically, we developed an AI-assisted claim prioritization prototype as a probe to explore how fact-checkers use multidimensional checkworthy factors to prioritize claims, simultaneously probing fact-checker needs and exploring the design space to meet those needs. With 16 professional fact-checkers participating in our study, we uncovered a hierarchical prioritization strategy fact-checkers implicitly use, revealing an underexplored aspect of their workflow, with actionable design recommendations for improving claim triage across multidimensional checkworthiness and tailoring this process with LLM integration.
This paper introduces DebateBrawl, an innovative AI-powered debate platform that integrates Large Language Models (LLMs), Genetic Algorithms (GA), and Adversarial Search (AS) to create an adaptive and engaging debating experience. DebateBrawl addresses the limitations of traditional LLMs in strategic planning by incorporating evolutionary optimization and game-theoretic techniques. The system demonstrates remarkable performance in generating coherent, contextually relevant arguments while adapting its strategy in real-time. Experimental results involving 23 debates show balanced outcomes between AI and human participants, with the AI system achieving an average score of 2.72 compared to the human average of 2.67 out of 10. User feedback indicates significant improvements in debating skills and a highly satisfactory learning experience, with 85% of users reporting improved debating abilities and 78% finding the AI opponent appropriately challenging. The system's ability to maintain high factual accuracy (92% compared to 78% in human-only debates) while generating diverse arguments addresses critical concerns in AI-assisted discourse. DebateBrawl not only serves as an effective educational tool but also contributes to the broader goal of improving public discourse through AI-assisted argumentation. The paper discusses the ethical implications of AI in persuasive contexts and outlines the measures implemented to ensure responsible development and deployment of the system, including robust fact-checking mechanisms and transparency in decision-making processes.
This study evaluates the effectiveness of Vision Language Models (VLMs) in representing and utilizing multimodal content for fact-checking. To be more specific, we investigate whether incorporating multimodal content improves performance compared to text-only models and how well VLMs utilize text and image information to enhance misinformation detection. Furthermore we propose a probing classifier based solution using VLMs. Our approach extracts embeddings from the last hidden layer of selected VLMs and inputs them into a neural probing classifier for multi-class veracity classification. Through a series of experiments on two fact-checking datasets, we demonstrate that while multimodality can enhance performance, fusing separate embeddings from text and image encoders yielded superior results compared to using VLM embeddings. Furthermore, the proposed neural classifier significantly outperformed KNN and SVM baselines in leveraging extracted embeddings, highlighting its effectiveness for multimodal fact-checking.