Differentially Private Semantic Plans for Aggregate Insight Generation

• URL: http://arxiv.org/abs/2609.16283v1
• Date: Mon, 14 Sep 2026 19:39:26 GMT
• Title: Differentially Private Semantic Plans for Aggregate Insight Generation
• Abstract summary: We introduce textttDP-SPIN, a trusted-curator framework for aggregate measurement and summarization over semantic concepts.<n>We evaluate textttDP-SPIN under record-level privacy on CFPB complaint narratives, Amazon All Beauty reviews, and Yelp restaurant reviews.
• Score: 4.832750949021042
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: \texttt{URANIA} provides end-to-end differential privacy (DP) for summaries of data-dependent clusters. However, its cluster--keyword release does not directly provide collection-wide aggregates for semantic concepts defined independently of the protected corpus. Records may express several concepts, records expressing the same concept may be assigned to different clusters, and cluster identities need not correspond across analyses. Consequently, cluster-level statistics do not directly provide comparable measurements of predefined concepts across collections or repeated analyses. We introduce \texttt{DP-SPIN}, a trusted-curator framework for aggregate measurement and summarization over semantic concepts fixed independently of the protected target records. Each record is mapped to a bounded sparse nonnegative vector over these concepts, whose sum forms a semantic sketch. A differentially private mechanism releases a semantic plan containing admitted concepts and noisy masses; normalized semantic-support values and support bins are obtained by post-processing. For user-level privacy, each user's aggregate contribution is clipped to a fixed bound. The language model receives only the plan and fixed decoding instructions, while a public verifier checks concept mentions, reported values, comparisons, and rank claims against the released plan. The final summary is differentially private by post-processing. We establish record- and user-level DP guarantees under add/drop and replacement adjacency. We evaluate \texttt{DP-SPIN} under record-level privacy on CFPB complaint narratives, Amazon All Beauty reviews, and Yelp restaurant reviews, and under user-level privacy on Amazon and Yelp. We compare \texttt{DP-SPIN} with non-private plan and summary references, DP keyword and category histogram baselines, and a \texttt{URANIA}-style baseline with a fixed public keyword vocabulary.

Related papers

• A Maximum Entropy Implementation of Differential Privacy Under Linear Invariants [0.8021197489470758]
  We propose a high entropy differential privacy implementation that maintains the aggregation invariants with probability one or exponentially close to one.<n>The methodology has general use in the context of sampling from normal mixture models under linear equality constraints.
  arXiv  Detail & Related papers  (2026-07-24T16:13:07Z)
• Interpretable Coreference Resolution Evaluation Using Explicit Semantics [35.71215348826291]
  Coreference resolution is evaluated using aggregate statistical metrics such as CoNLL-F1.<n>We introduce a semantically-enhanced evaluation framework for coreference resolution.<n>We show that our framework uncovers systematic weaknesses that remain obscured by aggregate metrics.
  arXiv  Detail & Related papers  (2026-05-11T14:20:16Z)
• Urania: Differentially Private Insights into AI Use [102.27238986985698]
  $Urania$ provides end-to-end privacy protection by leveraging DP tools such as clustering, partition selection, and histogram-based summarization.<n>Results show the framework's ability to extract meaningful conversational insights while maintaining stringent user privacy.
  arXiv  Detail & Related papers  (2025-06-05T07:00:31Z)
• Privacy-Preserving Conformal Prediction Under Local Differential Privacy [19.02072419946821]
  We propose two complementary approaches under local differential privacy (LDP)<n>In the first approach, users do not access the model but instead provide their input features and a perturbed label using a k-ary randomized response.<n>In the second approach, which enforces stricter privacy constraints, users add noise to their conformity score by binary search response.
  arXiv  Detail & Related papers  (2025-05-21T16:29:44Z)
• STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings [17.175065729425825]
  STAMP is a framework for detecting dataset membership.<n>We show that our framework can successfully detect contamination across four benchmarks which appear only once in the training data.
  arXiv  Detail & Related papers  (2025-04-18T02:25:08Z)
• Causal Unsupervised Semantic Segmentation [60.178274138753174]
  Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. We propose a novel framework, CAusal Unsupervised Semantic sEgmentation (CAUSE), which leverages insights from causal inference.
  arXiv  Detail & Related papers  (2023-10-11T10:54:44Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• Goal-Driven Explainable Clustering via Language Descriptions [50.980832345025334]
  We propose a new task formulation, "Goal-Driven Clustering with Explanations" (GoalEx) GoalEx represents both the goal and the explanations as free-form language descriptions. Our method produces more accurate and goal-related explanations than prior methods.
  arXiv  Detail & Related papers  (2023-05-23T07:05:50Z)
• SWING: Balancing Coverage and Faithfulness for Dialogue Summarization [67.76393867114923]
  We propose to utilize natural language inference (NLI) models to improve coverage while avoiding factual inconsistencies. We use NLI to compute fine-grained training signals to encourage the model to generate content in the reference summaries that have not been covered. Experiments on the DialogSum and SAMSum datasets confirm the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2023-01-25T09:33:11Z)
• DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection [118.36746273425354]
  This paper presents a paralleled visual-concept pre-training method for open-world detection by resorting to knowledge enrichment from a designed concept dictionary. By enriching the concepts with their descriptions, we explicitly build the relationships among various concepts to facilitate the open-domain learning. The proposed framework demonstrates strong zero-shot detection performances, e.g., on the LVIS dataset, our DetCLIP-T outperforms GLIP-T by 9.9% mAP and obtains a 13.5% improvement on rare categories.
  arXiv  Detail & Related papers  (2022-09-20T02:01:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.