NaSh: Guardrails for an LLM-Powered Natural Language Shell

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gyawali, Bimal Raj, Achalla, Saikrishna, Kallas, Konstantinos, Kumar, Sam
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915346251776000
author Gyawali, Bimal Raj
Achalla, Saikrishna
Kallas, Konstantinos
Kumar, Sam
author_facet Gyawali, Bimal Raj
Achalla, Saikrishna
Kallas, Konstantinos
Kumar, Sam
contents We explore how a shell that uses an LLM to accept natural language input might be designed differently from the shells of today. As LLMs may produce unintended or unexplainable outputs, we argue that a natural language shell should provide guardrails that empower users to recover from such errors. We concretize some ideas for doing so by designing a new shell called NaSh, identify remaining open problems in this space, and discuss research directions to address them.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13028
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NaSh: Guardrails for an LLM-Powered Natural Language Shell
Gyawali, Bimal Raj
Achalla, Saikrishna
Kallas, Konstantinos
Kumar, Sam
Operating Systems
Artificial Intelligence
We explore how a shell that uses an LLM to accept natural language input might be designed differently from the shells of today. As LLMs may produce unintended or unexplainable outputs, we argue that a natural language shell should provide guardrails that empower users to recover from such errors. We concretize some ideas for doing so by designing a new shell called NaSh, identify remaining open problems in this space, and discuss research directions to address them.
title NaSh: Guardrails for an LLM-Powered Natural Language Shell
topic Operating Systems
Artificial Intelligence
url https://arxiv.org/abs/2506.13028