paper-with-me

홈 › Papers

Truth Sleuth and Trend Bender: AI Agents to fact-check YouTube videos and influence opinions

2025-07-11 · Cécile Logé, Rehan Ghori arxiv

Misinformation poses a significant threat in today's digital world, often spreading rapidly through platforms like YouTube. This paper introduces a novel approach to combating misinformation by developing an AI-powered system that not only fact-checks claims made in YouTube videos but also actively engages users in the comment section and challenge misleading narratives. Our system comprises two main agents: Truth Sleuth and Trend Bender. Truth Sleuth extracts claims from a YouTube video, uses a Retrieval-Augmented Generation (RAG) approach - drawing on sources like Wikipedia, Google Search, Google FactCheck - to accurately assess their veracity and generates a nuanced and comprehensive report. Through rigorous prompt engineering, Trend Bender leverages this report along with a curated corpus of relevant articles to generate insightful and persuasive comments designed to stimulate a productive debate. With a carefully set up self-evaluation loop, this agent is able to iteratively improve its style and refine its output. We demonstrate the system's capabilities through experiments on established benchmark datasets and a real-world deployment on YouTube, showcasing its potential to engage users and potentially influence perspectives. Our findings highlight the high accuracy of our fact-checking agent, and confirm the potential of AI-driven interventions in combating misinformation and fostering a more informed online space.

📄 PDF Abstract BibTeX arXiv:2507.10577

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Track, Rank, Crack: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents

2026-07-14 · Ning Liu arxiv

Language agents that interleave reasoning and tool use degrade sharply as reasoning chains lengthen, even when each individual step is easy. We trace this to context dilution: an agent's investigative state (what it has …

Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs

2026-06-10 · Sanjay Adhikesaven, Haoxiang Sun, Sewon Min arxiv

Modern LLM training pipelines increasingly rely on other models to generate data, filter corpora, judge outputs, and guide development decisions. These dependencies are recursive: a model may depend on an upstream artifa…

Information Extraction

MOF-Sleuth: Tool-Grounded Reward Alignment for Explainable Fine-Grained MOF CIF Auditing

2026-07-22 · Yu Liu, Zhiwei Yang, Diandian Guo, Kun Peng 외 arxiv

Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs). Subtle chemical and structural errors in these inputs can compromise do…

Reinforcement Learning

Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding

2025-11-28 · Keliang Liu, Zizhi Chen, Mingcheng Li, Jingqun Tang 외 arxiv

Document understanding is a long standing practical task. Vision Language Models (VLMs) have gradually become a primary approach in this domain, demonstrating effective performance on single page tasks. However, their ef…

AcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora

2024-08-08 · Aleksandr Fedchin, Isabel Cooperman, Pramit Chaudhuri, Joseph P. Dexter

For centuries, writers have hidden messages in their texts as acrostics, where initial letters of consecutive lines or paragraphs form meaningful words or phrases. Scholars searching for acrostics manually can only focus…

Binary Classification