相关论文: MAD-Sherlock: Multi-Agent Debate for Visual Misinf…

In the human-bot symbiotic information ecosystem, social bots play key roles in spreading and correcting disinformation. Understanding their influence is essential for risk control and better governance. However, current studies often rely…

The detection and grounding of multimedia manipulation has emerged as a critical challenge in combating AI-generated disinformation. While existing methods have made progress in recent years, we identify two fundamental limitations in…

Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising…

Building user trust in dialogue agents requires smooth and consistent dialogue exchanges. However, agents can easily lose conversational context and generate irrelevant utterances. These situations are called dialogue breakdown, where agent…

The rapid proliferation of multimodal misinformation presents significant challenges for automated fact-checking systems, especially when claims are ambiguous or lack sufficient context. We introduce RAMA, a novel retrieval-augmented…

Large-scale dissemination of disinformation online intended to mislead or deceive the general population is a major societal problem. Rapid progression in image, video, and natural language generative models has only exacerbated this…

Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucination risks due to weak visual foundations. To address this,…

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority…

Detecting false information on social media is critical in mitigating its negative societal impacts. To reduce the propagation of false information, automated detection provide scalable, unbiased, and cost-effective methods. However, there…

Large Language Model-based Multi-Agent Systems (MASs) have demonstrated strong advantages in addressing complex real-world tasks. However, due to the introduction of additional attack surfaces, MASs are particularly vulnerable to…

The advent of large language models (LLMs) has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination emerging as a significant concern. Existing solutions often…

Misinformation on social media poses a critical threat to information credibility, as its diverse and context-dependent nature complicates detection. Large language model-empowered multi-agent systems (MAS) present a promising paradigm that…

Misinformation remains one of the most significant issues in the digital age. While automated fact-checking has emerged as a viable solution, most current systems are limited to evaluating factual accuracy. However, the detrimental effect…

In recent years, the spread of fake news has triggered a growing interest in Information Disorders (ID) on social media, a phenomenon that has become a focal point of research across fields ranging from complexity theory and computer…

The proliferation of misinformation on social media platforms has highlighted the need to understand how individual personality traits influence susceptibility to and propagation of misinformation. This study employs an innovative…

Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applications favor multi-agent architectures to manage complex…

While multi-agent debate has been proposed as a promising strategy for improving AI reasoning ability, we find that debate can sometimes be harmful rather than helpful. Prior work has primarily focused on debates within homogeneous groups…

Multi-agent debate (MAD) has recently emerged as a promising framework for improving the reasoning performance of large language models (LLMs). Yet, whether LLM agents can genuinely engage in deliberative reasoning, beyond simple ensembling…

Detecting out-of-context media, such as "mis-captioned" images on Twitter, is a relevant problem, especially in domains of high public significance. In this work we aim to develop defenses against such misinformation for the topics of…