Institution profile

Capital One

Industry researchnorthamerica · us
Official website
Research library163linked papers
Opportunities0open roles
Selected work

Representative Papers

EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors

Jan 31, 2026arXiv.org

This work addresses the inefficiency and high computational cost of existing privacy-preserving text generation methods in low-data regimes, which often fail to produce high-quality synthetic data. The authors propose a novel approach that constructs a differentially private “dataset vector” to capture the distributional discrepancy between private data and public priors in the activation space, leveraging this vector to guide large language models during text generation. By integrating dataset vectors with differential privacy for the first time, the method decouples the privacy budget from the generation process, enabling unlimited text synthesis without incurring additional privacy loss. Experiments demonstrate that the proposed method significantly outperforms current baselines under low-data conditions, achieving high fidelity in both distribution alignment and downstream task utility while substantially reducing computational overhead.

1 citationsRead paper

TARGET: Benchmarking Table Retrieval for Generative Tasks

May 14, 2025

Prior work on generative tasks (e.g., text-to-SQL, question answering) largely overlooks table retrieval—a critical prerequisite for leveraging structured data. Method: We introduce TARGET, the first table-level retrieval benchmark explicitly designed for generative tasks, featuring a structured evaluation framework with multi-source real-world tabular datasets, fine-grained human annotations, and an integrated retrieval-generation evaluation pipeline. Contribution/Results: Experiments show dense retrieval using BERT-based table encoders substantially outperforms BM25 (mAP gain >40%). Metadata absence—especially table titles—degrades performance by up to 35%. Significant performance disparities exist across datasets and tasks. Effective table retrieval boosts SQL generation accuracy by up to 22%. This work is the first to systematically quantify the impact of table retrieval on downstream generative performance and establishes a standardized evaluation paradigm for structured-data retrieval.

1 citationsRead paper
Recent publications

Latest Papers

The Rise of Verbal Reinforcement Learning

Sep 01, 2026

本文探讨了如何通过自然语言作为反馈来改进语言代理,提出了Verbal Reinforcement Learning框架,并根据语言反馈的作用时间和对象划分了三个主要领域。

0 citationsRead paper