paper-with-me

홈 › Papers

Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees

2025-08-28 · Stephen Meisenbacher, Maulik Chevli, Florian Matthes arxiv

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full document rewriting, and most often under local DP. Here, an input text must be made indistinguishable from any other potential text, within some bound governed by the privacy parameter $\varepsilon$. Such a guarantee is quite demanding, and recent works show that privatizing texts under local DP can only be done reasonably under very high $\varepsilon$ values. Addressing this challenge, we introduce DP-ST, which leverages semantic triples for neighborhood-aware private document generation under local DP guarantees. Through the evaluation of our method, we demonstrate the effectiveness of the divide-and-conquer paradigm, particularly when limiting the DP notion (and privacy guarantees) to that of a privatization neighborhood. When combined with LLM post-processing, our method allows for coherent text generation even at lower $\varepsilon$ values, while still balancing privacy and utility. These findings highlight the importance of coherence in achieving balanced privatization outputs at reasonable $\varepsilon$ levels.

📄 PDF Abstract BibTeX arXiv:2508.20736

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers

2024-03-22 · Kunal Sawarkar, Abhilasha Mangal, Shivam Raj Solanki

Retrieval-Augmented Generation (RAG) is a prevalent approach to infuse a private knowledge base of documents with Large Language Models (LLM) to build Generative Q\&A (Question-Answering) systems. However, RAG accuracy b…

Information RetrievalOpen-Domain Question AnsweringQuestion Answering+4

ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chains

2026-08-26 · Jinpu Jiang, Xuan Wu, Wenhao Song, Bo Yang 외 arxiv

Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for Question Answering (QA) by integrating external information into Large Language Models (LLMs). However, false, inaccurate, and misleading in…

Question Answering

Document-level Relation Extraction as Semantic Segmentation

2021-06-07 · Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng 외

Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of glob…

Document-level Relation ExtractionRelationRelation ExtractionSegmentation+1

KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering

2024-04-24 · Xinxin Zheng, Feihu Che, Jinyang Wu, Shuai Zhang 외

Large language models (LLMs) suffer from the hallucination problem and face significant challenges when applied to knowledge-intensive tasks. A promising approach is to leverage evidence documents as extra supporting kno…

HallucinationQuestion AnsweringRetrievalTriviaQA

Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

2022-04-24 · Feifei Xu, Shanlin Zhou, Xinpeng Wang, Yunpu Ma 외

Open-domain multi-turn conversations normally face the challenges of how to enrich and expand the content of the conversation. Recently, many approaches based on external knowledge are proposed to generate rich semantic …

Dialogue GenerationFormInformativenessKnowledge Graphs