Safe Language Generation in the Limit
This work addresses safety concerns in language generation for theoretical AI and computational linguistics, but it is incremental as it builds on existing learning in the limit paradigms.
The paper tackles the problem of safe language generation in the limit, proving that safe language identification is impossible and safe language generation is at least as hard as vanilla language identification, which is also impossible, while discussing some tractable cases.
Recent results in learning a language in the limit have shown that, although language identification is impossible, language generation is tractable. As this foundational area expands, we need to consider the implications of language generation in real-world settings. This work offers the first theoretical treatment of safe language generation. Building on the computational paradigm of learning in the limit, we formalize the tasks of safe language identification and generation. We prove that under this model, safe language identification is impossible, and that safe language generation is at least as hard as (vanilla) language identification, which is also impossible. Last, we discuss several intractable and tractable cases.