Reducing the Scope of Language Models

David Yunis; Siyu Huo; Chulaka Gunasekara; Danish Contractor

AAAI 2026technical0 citations

Reducing the Scope of Language Models

David Yunis, Siyu Huo, Chulaka Gunasekara, Danish Contractor

Abstract

Large language models (LLMs) are deployed in a wide variety of user-facing applications. Typically, these deployments have some specific purpose, like answering questions grounded on documentation or acting as coding assistants, but they require general language understanding. In such deployments, LLMs should respond only to queries that align with the intended purpose and reject all other requests, such as generating poetry or answering questions about physics, a task we refer to as

BibTeX

@inproceedings{aaai2026_reducingthescope,
  title = {Reducing the Scope of Language Models},
  author = {David Yunis and Siyu Huo and Chulaka Gunasekara and Danish Contractor},
  booktitle = {AAAI 2026},
  year = {2026}
}