@inproceedings{li-etal-2025-papillon,
title = "{PAPILLON}: Privacy Preservation from {I}nternet-based and Local Language Model Ensembles",
author = "Li, Siyan and
Raghuram, Vethavikashini Chithrra and
Khattab, Omar and
Hirschberg, Julia and
Yu, Zhou",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.173/",
doi = "10.18653/v1/2025.naacl-long.173",
pages = "3371--3390",
ISBN = "979-8-89176-189-6",
abstract = "Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user{'}s machine, alleviate some concerns, models that users can host locally are often less capable than proprietary frontier models. Toward preserving user privacy while retaining the best quality, we propose Privacy-Conscious Delegation, a novel task for chaining API-based and local models. We utilize recent public collections of user-LLM interactions to construct a natural benchmark called PUPA, which contains personally identifiable information (PII). To study potential approaches, we devise PAPILLON, a multi-stage LLM pipeline that uses prompt optimization to address a simpler version of our task. Our best pipeline maintains high response quality for 85.5{\%} of user queries while restricting privacy leakage to only 7.5{\%}. We still leave a large margin to the generation quality of proprietary LLMs for future work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-papillon">
<titleInfo>
<title>PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vethavikashini</namePart>
<namePart type="given">Chithrra</namePart>
<namePart type="family">Raghuram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Khattab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hirschberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user’s machine, alleviate some concerns, models that users can host locally are often less capable than proprietary frontier models. Toward preserving user privacy while retaining the best quality, we propose Privacy-Conscious Delegation, a novel task for chaining API-based and local models. We utilize recent public collections of user-LLM interactions to construct a natural benchmark called PUPA, which contains personally identifiable information (PII). To study potential approaches, we devise PAPILLON, a multi-stage LLM pipeline that uses prompt optimization to address a simpler version of our task. Our best pipeline maintains high response quality for 85.5% of user queries while restricting privacy leakage to only 7.5%. We still leave a large margin to the generation quality of proprietary LLMs for future work.</abstract>
<identifier type="citekey">li-etal-2025-papillon</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.173</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.173/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3371</start>
<end>3390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles
%A Li, Siyan
%A Raghuram, Vethavikashini Chithrra
%A Khattab, Omar
%A Hirschberg, Julia
%A Yu, Zhou
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F li-etal-2025-papillon
%X Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user’s machine, alleviate some concerns, models that users can host locally are often less capable than proprietary frontier models. Toward preserving user privacy while retaining the best quality, we propose Privacy-Conscious Delegation, a novel task for chaining API-based and local models. We utilize recent public collections of user-LLM interactions to construct a natural benchmark called PUPA, which contains personally identifiable information (PII). To study potential approaches, we devise PAPILLON, a multi-stage LLM pipeline that uses prompt optimization to address a simpler version of our task. Our best pipeline maintains high response quality for 85.5% of user queries while restricting privacy leakage to only 7.5%. We still leave a large margin to the generation quality of proprietary LLMs for future work.
%R 10.18653/v1/2025.naacl-long.173
%U https://aclanthology.org/2025.naacl-long.173/
%U https://doi.org/10.18653/v1/2025.naacl-long.173
%P 3371-3390
Markdown (Informal)
[PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles](https://aclanthology.org/2025.naacl-long.173/) (Li et al., NAACL 2025)
ACL
- Siyan Li, Vethavikashini Chithrra Raghuram, Omar Khattab, Julia Hirschberg, and Zhou Yu. 2025. PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3371–3390, Albuquerque, New Mexico. Association for Computational Linguistics.