The Ethical Need for Watermarks in Machine-Generated Language
This addresses ethical concerns for society by ensuring transparency in AI-generated content, though it is incremental as it builds on existing watermarking ideas.
The paper tackles the problem of distinguishing human from machine-generated text by proposing watermarks based on equidistant letter sequences, aiming to prevent manipulation and emotional distress.
Watermarks should be introduced in the natural language outputs of AI systems in order to maintain the distinction between human and machine-generated text. The ethical imperative to not blur this distinction arises from the asemantic nature of large language models and from human projections of emotional and cognitive states on machines, possibly leading to manipulation, spreading falsehoods or emotional distress. Enforcing this distinction requires unintrusive, yet easily accessible marks of the machine origin. We propose to implement a code based on equidistant letter sequences. While no such code exists in human-written texts, its appearance in machine-generated ones would prove helpful for ethical reasons.