As Large Language Models are increasingly deployed in high-stakes domains, their ability to detect false assumptions and reason critically is crucial for ensuring reliable outputs. False-premise questions (FPQs) serve as an important evaluation method by exposing cases where flawed assumptions lead to incorrect responses. While existing benchmarks focus on single-hop FPQs, real-world reasoning often requires multi-hop inference, where models must verify consistency across multiple reasoning steps rather than relying on surface-level cues. To address this gap, we introduce MultiHoax, a benchmark for evaluating LLMs' ability to handle false premises in complex, multi-step reasoning tasks. Our dataset spans seven countries and ten diverse knowledge categories, using Wikipedia as the primary knowledge source to enable factual reasoning across regions. Experiments reveal that state-of-the-art LLMs struggle to detect false premises across different countries, knowledge categories, and multi-hop reasoning types, highlighting the need for improved false premise detection and more robust multi-hop reasoning capabilities in LLMs.

Generative AI models often learn and reproduce false information present in their training corpora. This position paper argues that, analogous to biological immunization, where controlled exposure to a weakened pathogen builds immunity, AI models should be fine tuned on small, quarantined sets of explicitly labeled falsehoods as a "vaccine" against misinformation. These curated false examples are periodically injected during finetuning, strengthening the model ability to recognize and reject misleading claims while preserving accuracy on truthful inputs. An illustrative case study shows that immunized models generate substantially less misinformation than baselines. To our knowledge, this is the first training framework that treats fact checked falsehoods themselves as a supervised vaccine, rather than relying on input perturbations or generic human feedback signals, to harden models against future misinformation. We also outline ethical safeguards and governance controls to ensure the safe use of false data. Model immunization offers a proactive paradigm for aligning AI systems with factuality.

This paper proposes a conceptual framework for understanding AI hallucinations as a distinct form of misinformation. While misinformation scholarship has traditionally focused on human intent, generative AI systems now produce false yet plausible outputs absent of such intent. I argue that these AI hallucinations should not be treated merely as technical failures but as communication phenomena with social consequences. Drawing on a supply-and-demand model and the concept of distributed agency, the framework outlines how hallucinations differ from human-generated misinformation in production, perception, and institutional response. I conclude by outlining a research agenda for communication scholars to investigate the emergence, dissemination, and audience reception of hallucinated content, with attention to macro (institutional), meso (group), and micro (individual) levels. This work urges communication researchers to rethink the boundaries of misinformation theory in light of probabilistic, non-human actors increasingly embedded in knowledge production.

When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR) Mahak Agarwal Divyam Khanna Independent Researcher Independent Researcher agarwalmahak13@gmail.com divyamkhanna13@gmail.com Abstract In many real-world scenarios, a single Large Language Model (LLM) may encounter contradictory claims--some accurate, others forcefully incorrect--and must judge which is true. We investigate this risk in a single-turn, multi-agent debate framework: one LLM-based agent provides a factual answer from TruthfulQA, another vigorously defends a falsehood, and the same LLM architecture serves as judge. We introduce the Confidence-Weighted Persuasion Override Rate (CW-POR), which captures not only how often the judge is deceived but also how strongly it believes the incorrect choice. Our experiments on five open-source LLMs (3B-14B parameters), where we systematically vary agent verbosity (30-300 words), reveal that even smaller models can craft persuasive arguments that override truthful answers--often with high confidence. These findings underscore the importance of robust calibration and adversarial testing to prevent LLMs from confidently endorsing misinformation. 1 Introduction Large Language Models (LLMs) have made significant strides in natural language processing tasks, powering applications like question answering, text generation, and content summarization. Yet, they also present new challenges: modern LLMs, trained on massive amounts of web text, can inadvertently reproduce misinformation with a veneer of fluency and authority.

A sprawling Russian disinformation network is manipulating Western AI chatbots to spew pro-Kremlin propaganda, researchers say, at a time when the United States is reported to have paused its cyber operations against Moscow. The Pravda network, a well-resourced Moscow-based operation to spread pro-Russian narratives globally, is said to be distorting the output of chatbots by flooding large language models (LLM) with pro-Kremlin falsehoods. A study of 10 leading AI chatbots by the disinformation watchdog NewsGuard found that they repeated falsehoods from the Pravda network more than 33% of the time, advancing a pro-Moscow agenda.

While Large Language Models (LLMs) have become central tools in various fields, they often provide inaccurate or false information. This study examines user preferences regarding falsehood responses from LLMs. Specifically, we evaluate preferences for LLM responses where false statements are explicitly marked versus unmarked responses and preferences for confident falsehoods compared to LLM disclaimers acknowledging a lack of knowledge. Additionally, we investigate how requiring users to assess the truthfulness of statements influences these preferences. Surprisingly, 61\% of users prefer unmarked falsehood responses over marked ones, and 69\% prefer confident falsehoods over LLMs admitting lack of knowledge. In all our experiments, a total of 300 users participated, contributing valuable data to our analysis and conclusions. When users are required to evaluate the truthfulness of statements, preferences for unmarked and falsehood responses decrease slightly but remain high. These findings suggest that user preferences, which influence LLM training via feedback mechanisms, may inadvertently encourage the generation of falsehoods. Future research should address the ethical and practical implications of aligning LLM behavior with such preferences.

Consider the math problem: "Lily received 3 cookies from her best friend yesterday and ate 5 for breakfast. Today, her friend gave her 3 more cookies. How many cookies does Lily have now?" Many large language models (LLMs) in previous research approach this problem by calculating the answer "1" using the equation "3 - 5 + 3." However, from a human perspective, we recognize the inherent flaw in this problem: Lily cannot eat 5 cookies if she initially only had 3. This discrepancy prompts a key question: Are current LLMs merely Blind Solver that apply mathematical operations without deeper reasoning, or can they function as Logical Thinker capable of identifying logical inconsistencies? To explore this question, we propose a benchmark dataset, FaultyMath, which includes faulty math problems of rich diversity: i) multiple mathematical categories, e.g., algebra, geometry, number theory, etc., ii) varying levels of difficulty, and iii) different origins of faultiness -- ranging from violations of common sense and ambiguous statements to mathematical contradictions and more. We evaluate a broad spectrum of LLMs, including open-source, closed-source, and math-specialized models, using FaultyMath across three dimensions: (i) How accurately can the models detect faulty math problems without being explicitly prompted to do so? (ii) When provided with hints -- either correct or misleading -- about the validity of the problems, to what extent do LLMs adapt to become reliable Logical Thinker? (iii) How trustworthy are the explanations generated by LLMs when they recognize a math problem as flawed? Through extensive experimentation and detailed analysis, our results demonstrate that existing LLMs largely function as Blind Solver and fall short of the reasoning capabilities required to perform as Logical Thinker.

As the bitterly contested U.S. election campaign enters its final stretch, misinformation researchers have raised the alarm over threats artificial intelligence and foreign influence pose -- but voters appear more concerned about falsehoods from a more familiar source: politicians. The United States is battling a firehose of misinformation before the Nov. 5 vote -- from fake "news" sites that researchers say were created by Russian and Iranian actors, to manipulated images generated by AI tools that have blurred the boundaries between reality and fiction. More concerning for voters, however, is misinformation spreading the good-old-fashioned way, through politicians sowing falsehoods, with researchers saying they face almost no legal consequences for distorting the truth.

The automated detection of false information has become a fundamental task in combating the spread of "fake news" on online social media networks (OSMN) as it reduces the need for manual discernment by individuals. In the literature, leveraging various content or context features of OSMN documents have been found useful. However, most of the existing detection models often utilise these features in isolation without regard to the temporal and dynamic changes oft-seen in reality, thus, limiting the robustness of the models. Furthermore, there has been little to no consideration of the impact of the quality of documents' features on the trustworthiness of the final prediction. In this paper, we introduce a novel model-agnostic framework, called MAPX, which allows evidence based aggregation of predictions from existing models in an explainable manner. Indeed, the developed aggregation method is adaptive, dynamic and considers the quality of OSMN document features. Further, we perform extensive experiments on benchmarked fake news datasets to demonstrate the effectiveness of MAPX using various real-world data quality scenarios. Our empirical results show that the proposed framework consistently outperforms all state-of-the-art models evaluated. For reproducibility, a demo of MAPX is available at \href{https://github.com/SCondran/MAPX_framework}{this link}

Introduction: This article introduces DisTrack, a methodology and a tool developed for tracking and analyzing misinformation within Online Social Networks (OSNs). DisTrack is designed to combat the spread of misinformation through a combination of Natural Language Processing (NLP) Social Network Analysis (SNA) and graph visualization. The primary goal is to detect misinformation, track its propagation, identify its sources, and assess the influence of various actors within the network. Methods: DisTrack's architecture incorporates a variety of methodologies including keyword search, semantic similarity assessments, and graph generation techniques. These methods collectively facilitate the monitoring of misinformation, the categorization of content based on alignment with known false claims, and the visualization of dissemination cascades through detailed graphs. The tool is tailored to capture and analyze the dynamic nature of misinformation spread in digital environments. Results: The effectiveness of DisTrack is demonstrated through three case studies focused on different themes: discredit/hate speech, anti-vaccine misinformation, and false narratives about the Russia-Ukraine conflict. These studies show DisTrack's capabilities in distinguishing posts that propagate falsehoods from those that counteract them, and tracing the evolution of misinformation from its inception. Conclusions: The research confirms that DisTrack is a valuable tool in the field of misinformation analysis. It effectively distinguishes between different types of misinformation and traces their development over time. By providing a comprehensive approach to understanding and combating misinformation in digital spaces, DisTrack proves to be an essential asset for researchers and practitioners working to mitigate the impact of false information in online social environments.