# Model Attribution in LLM-Generated Disinformation: A Domain Generalization Approach with Supervised Contrastive Learning

arXiv: https://arxiv.org/abs/2407.21264 · HTML: https://mlsanity.com/paper/2407.21264/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 62 references that are in the map.
- First posted on arXiv 31 Jul 2024.

## Builds on (most cited first, 30 of 41)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [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)
- [Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning](https://mlsanity.com/paper/2011.01403/) (2020)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Better Fine-Tuning by Reducing Representational Collapse](https://mlsanity.com/paper/2008.03156/) (2020)
- [Neural Unsupervised Domain Adaptation in NLP---A Survey](https://mlsanity.com/paper/2006.00632/) (2020)
- [Maximum Mean Discrepancy Gradient Flow](https://mlsanity.com/paper/1906.04370/) (2019)
- [CoAID: COVID-19 Healthcare Misinformation Dataset](https://mlsanity.com/paper/2006.00885/) (2020)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks](https://mlsanity.com/paper/2310.10830/) (2023)
- ["Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models](https://mlsanity.com/paper/2406.19417/) (2024)
- [CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding](https://mlsanity.com/paper/2107.00440/) (2021)
- [Disinformation Detection: An Evolving Challenge in the Age of LLMs](https://mlsanity.com/paper/2309.15847/) (2023)
- [Can Large Language Models Identify Authorship?](https://mlsanity.com/paper/2403.08213/) (2024)
- [ConDA: Contrastive Domain Adaptation for AI-generated Text Detection](https://mlsanity.com/paper/2309.03992/) (2023)
- [Adversarial Deep Ensemble: Evasion Attacks and Defenses for Malware Detection](https://mlsanity.com/paper/2006.16545/) (2020)
- [Interpreting Pretrained Language Models via Concept Bottlenecks](https://mlsanity.com/paper/2311.05014/) (2023)
- [Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges](https://mlsanity.com/paper/2403.18249/) (2024)

## Built on by (most cited first, 2 of 2)

- [Who's Your Judge? On the Detectability of LLM-Generated Judgments](https://mlsanity.com/paper/2509.25154/) (2025)
- [Fine-Grained and Thematic Evaluation of LLMs in Social Deduction Game](https://mlsanity.com/paper/2408.09946/) (2024)

## Abstract (arXiv)

Model attribution for LLM-generated disinformation poses a significant challenge in understanding its origins and mitigating its spread. This task is especially challenging because modern large language models (LLMs) produce disinformation with human-like quality. Additionally, the diversity in prompting methods used to generate disinformation complicates accurate source attribution. These methods introduce domain-specific features that can mask the fundamental characteristics of the models. In this paper, we introduce the concept of model attribution as a domain generalization problem, where each prompting method represents a unique domain. We argue that an effective attribution model must be invariant to these domain-specific features. It should also be proficient in identifying the originating models across all scenarios, reflecting real-world detection challenges. To address this, we introduce a novel approach based on Supervised Contrastive Learning. This method is designed to enhance the model's robustness to variations in prompts and focuses on distinguishing between different source LLMs. We evaluate our model through rigorous experiments involving three common prompting methods: ``open-ended'', ``rewriting'', and ``paraphrasing'', and three advanced LLMs: ``llama 2'', ``chatgpt'', and ``vicuna''. Our results demonstrate the effectiveness of our approach in model attribution tasks, achieving state-of-the-art performance across diverse and unseen datasets.