Hidden Persuaders: LLMs’ Political Leaning and Their Influence on Voters
Authors:
Top Cited Papers
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 4244-4275
Abstract
Yujin Potter, Shiyang Lai, Junsol Kim, James Evans, Dawn Song. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- How persuasive is AI-generated propaganda?PNAS Nexus, 2024
- The Self-Perception and Political Biases of ChatGPTHuman Behavior and Emerging Technologies, 2024
- On the Relationship between Truth and Political Bias in Language Models2024
- Systematic Biases in LLM Simulations of Debates2024
- SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling2024
- More human than human: measuring ChatGPT political biasPublic Choice, 2023
- From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models2023