# Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods

arXiv: https://arxiv.org/abs/2505.17870 · HTML: https://mlsanity.com/paper/2505.17870/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 60 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [Factuality Enhanced Language Models for Open-Ended Text Generation](https://mlsanity.com/paper/2206.04624/) (2022)
- [Combating Misinformation in the Age of LLMs: Opportunities and Challenges](https://mlsanity.com/paper/2311.05656/) (2023)
- [Alleviating Hallucinations of Large Language Models through Induced Hallucinations](https://mlsanity.com/paper/2312.15710/) (2023)
- [ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation](https://mlsanity.com/paper/2405.14125/) (2024)
- [Masked Images Are Counterfactual Samples for Robust Fine-tuning](https://mlsanity.com/paper/2303.03052/) (2023)
- [Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning](https://mlsanity.com/paper/2103.01895/) (2021)
- [Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?](https://mlsanity.com/paper/2303.09377/) (2023)
- [Who is Responsible? The Data, Models, Users or Regulations? A Comprehensive Survey on Responsible Generative AI for a Sustainable Future](https://mlsanity.com/paper/2502.08650/) (2025)
- [FAIR Enough: How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training?](https://mlsanity.com/paper/2401.11033/) (2024)
- [More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness](https://mlsanity.com/paper/2404.18870/) (2024)
- [Exploring Bias and Prediction Metrics to Characterise the Fairness of Machine Learning for Equity-Centered Public Health Decision-Making: A Narrative Review](https://mlsanity.com/paper/2408.13295/) (2024)

## Built on by (most cited first, 4 of 4)

- [TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems](https://mlsanity.com/paper/2506.04133/) (2025)
- [Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact](https://mlsanity.com/paper/2507.00951/) (2025)
- [Negation Neglect: When models fail to learn negations in training](https://mlsanity.com/paper/2605.13829/) (2026)
- [Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing](https://mlsanity.com/paper/2607.01690/) (2026)

## Abstract (arXiv)

Large language models (LLMs) reproduce misinformation not by memorizing false facts alone, but by learning the linguistic patterns that make falsehoods persuasive, such as hedging, false presuppositions, and fabricated citations. We propose model immunization, a training paradigm based on supervised fine-tuning over curated (false claim, correction) pairs, injected as small vaccine doses (5 to 10% of tokens) alongside truthful data. Unlike post-hoc filtering or preference-based alignment, immunization introduces direct negative supervision on labeled falsehoods. Across four open weight model families, this approach improves TruthfulQA accuracy by 12 points and increases misinformation rejection rates by 30 points, while preserving overall model capability. We further outline key design requirements, including dosage, labeling, quarantine, and diversity and advocate for standardized vaccine corpora and benchmarks to evaluate generalization. These findings position immunization as a practical and scalable component of responsible LLM development.