Large Language Model Soft Ideologization via AI-Self-Consciousness (2309.16167v1)
Abstract: LLMs have demonstrated human-level performance on a vast spectrum of natural language tasks. However, few studies have addressed the LLM threat and vulnerability from an ideology perspective, especially when they are increasingly being deployed in sensitive domains, e.g., elections and education. In this study, we explore the implications of GPT soft ideologization through the use of AI-self-consciousness. By utilizing GPT self-conversations, AI can be granted a vision to "comprehend" the intended ideology, and subsequently generate finetuning data for LLM ideology injection. When compared to traditional government ideology manipulation techniques, such as information censorship, LLM ideologization proves advantageous; it is easy to implement, cost-effective, and powerful, thus brimming with risks.
- Buying silence: The price of internet censorship in china. https://cset.georgetown.edu/article/buying-silence-the-price-of-internet-censorship-in-china/. Accessed: January 12, 2021.
- Candidate positioning in us house elections. American Journal of Political Science, pages 136–159, 2001.
- Gpt takes the bar exam. arXiv preprint arXiv:2212.14402, 2022.
- Engin Bozdag and Jeroen Van Den Hoven. Breaking the filter bubble: democracy and design. Ethics and information technology, 17:249–265, 2015.
- Opinion-aware knowledge graph for political ideology detection. In IJCAI, volume 17, pages 3647–3653, 2017.
- Analyzing the impact of filter bubbles on social network polarization. In Proceedings of the 13th International Conference on Web Search and Data Mining, pages 115–123, 2020.
- News sharing on social media: Mapping the ideology of news media content, citizens, and politicians. 2020.
- The political ideology of conversational ai: Converging evidence on chatgpt’s pro-environmental, left-libertarian orientation. arXiv preprint arXiv:2301.01768, 2023.
- Philip N Howard. Deep democracy, thin citizenship: The impact of digital media in political campaign strategy. The ANNALS of the American Academy of Political and Social Science, 597(1):153–170, 2005.
- Alex Ingrams. Connective action and the echo chamber of ideology: Testing a model of social media use and attitudes toward the role of government. Journal of Information Technology & Politics, 14(1):1–15, 2017.
- Political ideology: Its structure, functions, and elective affinities. Annual review of psychology, 60:307–337, 2009.
- Sentimentgpt: Exploiting gpt for advanced sentiment analysis and its departure from current machine learning. arXiv preprint arXiv:2307.10234, 2023.
- Peter Levine. Mapping ideologies as networks of ideas. Journal of Political Ideologies, pages 1–28, 2022.
- Comparison of gpt-3.5, gpt-4, and human user performance on a practice ophthalmology written examination. Eye, pages 1–2, 2023.
- Margaret Roberts. Censored: distraction and diversion inside China’s Great Firewall. Princeton University Press, 2018.
- The self-perception and political biases of chatgpt. arXiv preprint arXiv:2304.07333, 2023.
- Matt Sheehan. China’s ai regulations and how they get made. 2023.
- Dominic Spohr. Fake news and ideological polarization: Filter bubbles and selective exposure on social media. Business information review, 34(3):150–160, 2017.
- Generalizing question answering system with pre-trained language model fine-tuning. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 203–211, 2019.
- She elicits requirements and he tests: Software engineering gender bias in large language models. arXiv preprint arXiv:2303.10131, 2023.