# Large Language Models Reveal Information Operation Goals, Tactics, and Narrative Frames

arXiv: https://arxiv.org/abs/2405.03688 · HTML: https://mlsanity.com/paper/2405.03688/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 91 references that are in the map.
- First posted on arXiv 6 May 2024.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [The False Promise of Imitating Proprietary LLMs](https://mlsanity.com/paper/2305.15717/) (2023)
- [LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples](https://mlsanity.com/paper/2310.01469/) (2023)
- [Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP](https://mlsanity.com/paper/2109.02748/) (2021)
- [An empirical study of LLaMA3 quantization: from LLMs to MLLMs](https://mlsanity.com/paper/2404.14047/) (2024)
- [Uncovering Coordinated Networks on Social Media: Methods and Case Studies](https://mlsanity.com/paper/2001.05658/) (2020)
- [Identifying Coordinated Accounts on Social Media through Hidden Influence and Group Behaviours](https://mlsanity.com/paper/2008.11308/) (2020)
- [Analyzing the Digital Traces of Political Manipulation: The 2016 Russian Interference Twitter Campaign](https://mlsanity.com/paper/1802.04291/) (2018)
- [Disinformation and Social Bot Operations in the Run Up to the 2017 French Presidential Election](https://mlsanity.com/paper/1707.00086/) (2017)
- [Bots increase exposure to negative and inflammatory content in online social systems](https://mlsanity.com/paper/1802.07292/) (2018)
- [How Susceptible are Large Language Models to Ideological Manipulation?](https://mlsanity.com/paper/2402.11725/) (2024)
- [Coordinated Behavior on Social Media in 2019 UK General Election](https://mlsanity.com/paper/2008.08370/) (2020)
- [Unmasking the Web of Deceit: Uncovering Coordinated Activity to Expose Information Operations on Twitter](https://mlsanity.com/paper/2310.09884/) (2023)
- [Leveraging Large Language Models to Detect Influence Campaigns in Social Media](https://mlsanity.com/paper/2311.07816/) (2023)
- [Characterizing the 2016 Russian IRA Influence Campaign](https://mlsanity.com/paper/1812.01997/) (2018)
- [Bots, #StrongerIn, and #Brexit: Computational Propaganda during the UK-EU Referendum](https://mlsanity.com/paper/1606.06356/) (2016)
- [Auditing Elon Musk's Impact on Hate Speech and Bots](https://mlsanity.com/paper/2304.04129/) (2023)
- [Socio-Linguistic Characteristics of Coordinated Inauthentic Accounts](https://mlsanity.com/paper/2305.11867/) (2023)
- [Open World Classification with Adaptive Negative Samples](https://mlsanity.com/paper/2303.05581/) (2023)

## Abstract (arXiv)

Adversarial information operations can destabilize societies by undermining fair elections, manipulating public opinions on policies, and promoting scams. Despite their widespread occurrence and potential impacts, our understanding of influence campaigns is limited by manual analysis of messages and subjective interpretation of their observable behavior. In this paper, we explore whether these limitations can be mitigated with large language models (LLMs), using GPT-3.5 as a case-study for coordinated campaign annotation. We first use GPT-3.5 to scrutinize 126 identified information operations spanning over a decade. We utilize a number of metrics to quantify the close (if imperfect) agreement between LLM and ground truth descriptions. We next extract coordinated campaigns from two large multilingual datasets from X (formerly Twitter) that respectively discuss the 2022 French election and 2023 Balikaran Philippine-U.S. military exercise in 2023. For each coordinated campaign, we use GPT-3.5 to analyze posts related to a specific concern and extract goals, tactics, and narrative frames, both before and after critical events (such as the date of an election). While the GPT-3.5 sometimes disagrees with subjective interpretation, its ability to summarize and interpret demonstrates LLMs' potential to extract higher-order indicators from text to provide a more complete picture of the information campaigns compared to previous methods.