@inproceedings{fan-etal-2025-ppc,
title = "{PPC}-{GPT}: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation",
author = "Fan, Tao and
Ma, Guoqiang and
Song, Yuanfeng and
Fan, Lixin and
Yang, Qiang",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.747/",
pages = "14794--14805",
ISBN = "979-8-89176-332-6",
abstract = "Compressing Large Language Models (LLMs) into task-specific Small Language Models (SLMs) encounters two significant challenges: safeguarding domain-specific knowledge privacy and managing limited resources. To tackle these challenges, we propose PPC-GPT, a novel unified framework that systematically addresses both privacy preservation and model compression in federated settings. PPC-GPT works on a server-client federated architecture, where the client sends differentially private (DP) perturbed task-specific data to the server{'}s LLM. The LLM then generates synthetic data along with their corresponding rationales. This synthetic data is subsequently used for both LLM pruning and retraining processes. Our framework{'}s key innovation lies in its holistic integration of privacy-preserving mechanisms, synthetic data generation, and task-specific compression techniques, creating unique benefits through component interaction. Our experiments across diverse text generation tasks demonstrate that PPC-GPT successfully achieves dual objectives: maintaining competitive performance comparable to full-sized LLMs while ensuring robust privacy protection through its federated architecture. Our code has been contributed to the FATE open-source project and is now publicly accessible at \textit{ \url{https://github.com/FederatedAI/FATE-LLM/tree/main/python/fate_llm/algo/ppc-gpt}}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2025-ppc">
<titleInfo>
<title>PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoqiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanfeng</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lixin</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Compressing Large Language Models (LLMs) into task-specific Small Language Models (SLMs) encounters two significant challenges: safeguarding domain-specific knowledge privacy and managing limited resources. To tackle these challenges, we propose PPC-GPT, a novel unified framework that systematically addresses both privacy preservation and model compression in federated settings. PPC-GPT works on a server-client federated architecture, where the client sends differentially private (DP) perturbed task-specific data to the server’s LLM. The LLM then generates synthetic data along with their corresponding rationales. This synthetic data is subsequently used for both LLM pruning and retraining processes. Our framework’s key innovation lies in its holistic integration of privacy-preserving mechanisms, synthetic data generation, and task-specific compression techniques, creating unique benefits through component interaction. Our experiments across diverse text generation tasks demonstrate that PPC-GPT successfully achieves dual objectives: maintaining competitive performance comparable to full-sized LLMs while ensuring robust privacy protection through its federated architecture. Our code has been contributed to the FATE open-source project and is now publicly accessible at https://github.com/FederatedAI/FATE-LLM/tree/main/python/fate_llm/algo/ppc-gpt</abstract>
<identifier type="citekey">fan-etal-2025-ppc</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.747/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>14794</start>
<end>14805</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation
%A Fan, Tao
%A Ma, Guoqiang
%A Song, Yuanfeng
%A Fan, Lixin
%A Yang, Qiang
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F fan-etal-2025-ppc
%X Compressing Large Language Models (LLMs) into task-specific Small Language Models (SLMs) encounters two significant challenges: safeguarding domain-specific knowledge privacy and managing limited resources. To tackle these challenges, we propose PPC-GPT, a novel unified framework that systematically addresses both privacy preservation and model compression in federated settings. PPC-GPT works on a server-client federated architecture, where the client sends differentially private (DP) perturbed task-specific data to the server’s LLM. The LLM then generates synthetic data along with their corresponding rationales. This synthetic data is subsequently used for both LLM pruning and retraining processes. Our framework’s key innovation lies in its holistic integration of privacy-preserving mechanisms, synthetic data generation, and task-specific compression techniques, creating unique benefits through component interaction. Our experiments across diverse text generation tasks demonstrate that PPC-GPT successfully achieves dual objectives: maintaining competitive performance comparable to full-sized LLMs while ensuring robust privacy protection through its federated architecture. Our code has been contributed to the FATE open-source project and is now publicly accessible at https://github.com/FederatedAI/FATE-LLM/tree/main/python/fate_llm/algo/ppc-gpt
%U https://aclanthology.org/2025.emnlp-main.747/
%P 14794-14805
Markdown (Informal)
[PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation](https://aclanthology.org/2025.emnlp-main.747/) (Fan et al., EMNLP 2025)
ACL