# The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence

arXiv: https://arxiv.org/abs/2601.05478 · HTML: https://mlsanity.com/paper/2601.05478/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 84 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 30 of 46)

- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media](https://mlsanity.com/paper/1809.01286/) (2018)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction](https://mlsanity.com/paper/2312.13558/) (2023)
- [The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation](https://mlsanity.com/paper/2312.09085/) (2023)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours](https://mlsanity.com/paper/1704.05972/) (2017)
- [Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks](https://mlsanity.com/paper/2310.10830/) (2023)
- [LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction](https://mlsanity.com/paper/2312.12343/) (2023)
- [Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation](https://mlsanity.com/paper/2310.15515/) (2023)
- [AutoBencher: Towards Declarative Benchmark Construction](https://mlsanity.com/paper/2407.08351/) (2024)
- [The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents](https://mlsanity.com/paper/2410.19064/) (2024)
- [Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation](https://mlsanity.com/paper/2412.13666/) (2024)
- [Automatically Identifying Fake News in Popular Twitter Threads](https://mlsanity.com/paper/1705.01613/) (2017)
- [How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation](https://mlsanity.com/paper/2503.09598/) (2025)
- [Matching Tweets With Applicable Fact-Checks Across Languages](https://mlsanity.com/paper/2202.07094/) (2022)
- [RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information](https://mlsanity.com/paper/2406.11093/) (2024)
- [Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning](https://mlsanity.com/paper/2505.16836/) (2025)
- [Learn and Unlearn: Addressing Misinformation in Multilingual LLMs](https://mlsanity.com/paper/2406.13748/) (2024)
- [Real-time Factuality Assessment from Adversarial Feedback](https://mlsanity.com/paper/2410.14651/) (2024)
- [PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation](https://mlsanity.com/paper/2506.06842/) (2025)
- [Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation](https://mlsanity.com/paper/2405.04325/) (2024)
- [Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models](https://mlsanity.com/paper/2410.20940/) (2024)
- [TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection](https://mlsanity.com/paper/2509.04448/) (2025)
- [Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation](https://mlsanity.com/paper/2510.11423/) (2025)
- [Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?](https://mlsanity.com/paper/2410.13517/) (2024)

## Built on by (most cited first, 3 of 3)

- [Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs](https://mlsanity.com/paper/2608.11624/) (2026)
- [The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2606.03032/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)

## Abstract (arXiv)

To reliably assist human decision-making, LLMs must maintain factual internal beliefs against misleading injections. While current models resist explicit misinformation, we uncover a fundamental vulnerability to sophisticated, hard-to-falsify evidence. To systematically probe this weakness, we introduce MisBelief, a framework that generates misleading evidence via collaborative, multi-round interactions among multi-role LLMs. This process mimics subtle, defeasible reasoning and progressive refinement to create logically persuasive yet factually deceptive claims. Using MisBelief, we generate 4,800 instances across three difficulty levels to evaluate 7 representative LLMs. Results indicate that while models are robust to direct misinformation, they are highly sensitive to this refined evidence: belief scores in falsehoods increase by an average of 93.0%, fundamentally compromising downstream recommendations. To address this, we propose Deceptive Intent Shielding (DIS), a governance mechanism that provides an early warning signal by inferring the deceptive intent behind evidence. Empirical results demonstrate that DIS consistently mitigates belief shifts and promotes more cautious evidence evaluation.