mlsanityData to 14 Oct 2026

Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks

arXiv 2510.08605 ↗First posted 7 Oct 2025cs.CL cs.AI cs.CRcited by 1

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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 transformations examined in this paper have not been systematically studied. In particular, we investigate language-switching across English, French, Spanish, Arabic, Hindi, and Chinese, followed by translation. We also study query length inflation preceding summarization and structural reformatting into multiple-choice questions. In this paper, we present a multilingual, multi-agent large language model framework with retrieval-augmented generation that can be deployed as a web plugin into online platforms. Our work underscores the importance of AI-driven misinformation detection in safeguarding online factual integrity against diverse attacks, while showcasing the feasibility of plugin-based deployment for real-world web applications.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 20 of its 47 references that are in the map. First posted on arXiv 7 Oct 2025.

Builds on

20 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identification23 May
  2. 2025The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News13 May

Other references · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  5. 2021Ethical and social risks of harm from Language Modelscited by 966
  6. 2019Defending Against Neural Fake Newscited by 559
  7. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 372
  8. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 141
  9. 2022MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Datasetcited by 61
  10. 2023Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4cited by 45
  11. 2022Synthetic Disinformation Attacks on Automated Fact Verification Systemscited by 44
  12. 2023The Perils & Promises of Fact-checking with Large Language Modelscited by 31
6 more
  1. 2022Domain Adaptive Fake News Detection via Reinforcement Learningcited by 27
  2. 2024Large language models can consistently generate high-quality content for election disinformation operationscited by 14
  3. 2024Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuningcited by 8
  4. 2024Generative AI for automatic topic labellingcited by 5
  5. 2024AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoningcited by 3
  6. 2025CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerabilitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents
  2. 2025Toward Verifiable Misinformation Detection: A Multi-Tool LLM Agent Framework
  3. 2025Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies
  4. 2025A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation Detection
  5. 2026A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
  6. 2025Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models
  7. 2025X-Guard: Multilingual Guard Agent for Content Moderation
  8. 2024Web Retrieval Agents for Evidence-Based Misinformation Detection