Can LLM-Generated Misinformation Be Detected?
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Large Language Models, misinformation
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We discover that LLM-generated misinformation can be harder to detect for humans and detectors compared to human-written misinformation with the same semantics, which suggests it can have more deceptive styles and potentially cause more harm.
Abstract: The advent of Large Language Models (LLMs) has made a transformative impact. However, the potential that LLMs such as ChatGPT can be exploited to generate misinformation has posed a serious concern to online safety and public trust. A fundamental research question is: will LLM-generated misinformation cause more harm than human-written misinformation? We propose to tackle this question from the perspective of detection difficulty. We first build a taxonomy of LLM-generated misinformation. Then we categorize and validate the potential real-world methods for generating misinformation with LLMs. Then, through extensive empirical investigation, we discover that LLM-generated misinformation can be harder to detect for humans and detectors compared to human-written misinformation with the same semantics, which suggests it can have more deceptive styles and potentially cause more harm. We also discuss the implications of our discovery on combating misinformation in the age of LLMs and the countermeasures.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: societal considerations including fairness, safety, privacy
Submission Number: 7983
Loading