@inproceedings{rebedea-etal-2023-nemo,
title = "{N}e{M}o Guardrails: A Toolkit for Controllable and Safe {LLM} Applications with Programmable Rails",
author = "Rebedea, Traian and
Dinu, Razvan and
Sreedhar, Makesh Narsimhan and
Parisien, Christopher and
Cohen, Jonathan",
editor = "Feng, Yansong and
Lefever, Els",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-demo.40",
doi = "10.18653/v1/2023.emnlp-demo.40",
pages = "431--445",
abstract = "NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. Guardrails (or rails for short) are a specific way of controlling the output of an LLM, such as not talking about topics considered harmful, following a predefined dialogue path, using a particular language style, and more. There are several mechanisms that allow LLM providers and developers to add guardrails that are embedded into a specific model at training, e.g. using model alignment. Using a runtime inspired from dialogue management, NeMo Guardrails provides a different approach by allowing developers to add programmable rails to LLM applications - these are user-defined, independent of the underlying LLM, and interpretable. Our initial results show that the proposed approach can be used with several LLM providers to develop controllable and safe LLM applications using programmable rails.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rebedea-etal-2023-nemo">
<titleInfo>
<title>NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails</title>
</titleInfo>
<name type="personal">
<namePart type="given">Traian</namePart>
<namePart type="family">Rebedea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Razvan</namePart>
<namePart type="family">Dinu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makesh</namePart>
<namePart type="given">Narsimhan</namePart>
<namePart type="family">Sreedhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Parisien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. Guardrails (or rails for short) are a specific way of controlling the output of an LLM, such as not talking about topics considered harmful, following a predefined dialogue path, using a particular language style, and more. There are several mechanisms that allow LLM providers and developers to add guardrails that are embedded into a specific model at training, e.g. using model alignment. Using a runtime inspired from dialogue management, NeMo Guardrails provides a different approach by allowing developers to add programmable rails to LLM applications - these are user-defined, independent of the underlying LLM, and interpretable. Our initial results show that the proposed approach can be used with several LLM providers to develop controllable and safe LLM applications using programmable rails.</abstract>
<identifier type="citekey">rebedea-etal-2023-nemo</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-demo.40</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-demo.40</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>431</start>
<end>445</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails
%A Rebedea, Traian
%A Dinu, Razvan
%A Sreedhar, Makesh Narsimhan
%A Parisien, Christopher
%A Cohen, Jonathan
%Y Feng, Yansong
%Y Lefever, Els
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F rebedea-etal-2023-nemo
%X NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. Guardrails (or rails for short) are a specific way of controlling the output of an LLM, such as not talking about topics considered harmful, following a predefined dialogue path, using a particular language style, and more. There are several mechanisms that allow LLM providers and developers to add guardrails that are embedded into a specific model at training, e.g. using model alignment. Using a runtime inspired from dialogue management, NeMo Guardrails provides a different approach by allowing developers to add programmable rails to LLM applications - these are user-defined, independent of the underlying LLM, and interpretable. Our initial results show that the proposed approach can be used with several LLM providers to develop controllable and safe LLM applications using programmable rails.
%R 10.18653/v1/2023.emnlp-demo.40
%U https://aclanthology.org/2023.emnlp-demo.40
%U https://doi.org/10.18653/v1/2023.emnlp-demo.40
%P 431-445
Markdown (Informal)
[NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://aclanthology.org/2023.emnlp-demo.40) (Rebedea et al., EMNLP 2023)
ACL