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

Multimodal Large Language Models (MLLMs) in healthcare suffer from severe confirmation bias, often hallucinating visual details to support initial, potentially erroneous diagnostic hypotheses. Existing Chain-of-Thought (CoT) approaches lack…

Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared to traditional text-only information. While existing…

This paper develops an agent-based automated fact-checking approach for detecting misinformation. We demonstrate that combining a powerful LLM agent, which does not have access to the internet for searches, with an online web search agent…

Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidious and destructive safety risks, namely deception. Unlike…

In this paper, we delve into the rapidly evolving challenge of misinformation detection, with a specific focus on the nuanced manipulation of narrative frames - an under-explored area within the AI community. The potential for Generative AI…

The rapid spread of misinformation on digital platforms threatens public discourse, emotional stability, and decision-making. While prior work has explored various adversarial attacks in misinformation detection, the specific…

Recent advancements in large language models (LLMs) underscore their potential for responding to inquiries in various domains. However, ensuring that generative agents provide accurate and reliable answers remains an ongoing challenge. In…

Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost. Studies…

Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are compromised on erroneous reasoning. Existing methods lack…

Misinformation is a global problem in modern social media platforms with few solutions known to be effective. Social media platforms have offered tools to raise awareness of information, but these are closed systems that have not been…

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only…

The rise of micro-videos has reshaped how misinformation spreads, amplifying its speed, reach, and impact on public trust. Existing benchmarks typically focus on a single deception type, overlooking the diversity of real-world cases that…

Accurate detection of errors in large language models (LLM) responses is central to the success of scalable oversight, or providing effective supervision to superhuman intelligence. Yet, self-diagnosis is often unreliable on complex tasks…

Preventing the spread of misinformation is challenging. The detection of misleading content presents a significant hurdle due to its extreme linguistic and domain variability. Content-based models have managed to identify deceptive language…

The widespread prevalence of misinformation poses significant societal concerns. Out-of-context misinformation, where authentic images are paired with false text, is particularly deceptive and easily misleads audiences. Most existing…

Online disinformation poses an escalating threat to society, driven increasingly by the rapid spread of misleading content across both multimedia and multilingual platforms. While automated fact-checking methods have advanced in recent…

Misinformation continues to pose a significant challenge in today's information ecosystem, profoundly shaping public perception and behavior. Among its various manifestations, Out-of-Context (OOC) misinformation is particularly obscure, as…

Multi-agent debate (MAD) aims to improve large language model (LLM) reasoning by letting multiple agents exchange answers and then aggregate their opinions. Yet recent studies reveal that agents are not neutral: they are prone to…

Large Language Models (LLMs) have advanced autonomous agents' planning and decision-making, yet they struggle with complex tasks requiring diverse expertise and multi-step reasoning. Multi-Agent Debate (MAD) systems, introduced in NLP…

Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging. Existing methods often face difficulties with contextual…