paper-with-me

홈 › Papers

On Synthetic Data Strategies for Domain-Specific Generative Retrieval

2025-02-25 · Haoyang Wen, Jiang Guo, Yi Zhang, Jiarong Jiang, Zhiguo Wang

This paper investigates synthetic data generation strategies in developing generative retrieval models for domain-specific corpora, thereby addressing the scalability challenges inherent in manually annotating in-domain queries. We study the data strategies for a two-stage training framework: in the first stage, which focuses on learning to decode document identifiers from queries, we investigate LLM-generated queries across multiple granularity (e.g. chunks, sentences) and domain-relevant search constraints that can better capture nuanced relevancy signals. In the second stage, which aims to refine document ranking through preference learning, we explore the strategies for mining hard negatives based on the initial model's predictions. Experiments on public datasets over diverse domains demonstrate the effectiveness of our synthetic data generation and hard negative sampling approach.

📄 PDF Abstract BibTeX arXiv:2502.17957

Code (0)

등록된 구현이 없습니다.

Tasks

Document RankingRetrievalSynthetic Data Generation

Similar Papers 제목 키워드 기반

Generating Reliable Synthetic Clinical Trial Data: The Role of Hyperparameter Optimization and Domain Constraints

2025-05-08 · Waldemar Hahn, Jan-Niklas Eckardt, Christoph Röllig, Martin Sedlmayr 외

The generation of synthetic clinical trial data offers a promising approach to mitigating privacy concerns and data accessibility limitations in medical research. However, ensuring that synthetic datasets maintain high f…

Hyperparameter OptimizationSynthetic Data Generation

Time Series Deinterleaving of DNS Traffic

2018-07-16 · Amir Asiaee, Hardik Goel, Shalini Ghosh, Vinod Yegneswaran 외

Stream deinterleaving is an important problem with various applications in the cybersecurity domain. In this paper, we consider the specific problem of deinterleaving DNS data streams using machine-learning techniques, w…

BIG-bench Machine LearningTime SeriesTime Series Analysis

Single-Shot Domain Adaptation via Target-Aware Generative Augmentation

2022-10-29 · Rakshith Subramanyam, Kowshik Thopalli, Spring Berman, Pavan Turaga 외

The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks. While several test-time adaptation te…

AttributeDomain AdaptationTest-time Adaptation

The Impact of Synthetic Data on Object Detection Model Performance: A Comparative Analysis with Real-World Data

2025-10-14 · Muammer Bay, Timo von Marcard, Dren Fazlija arxiv

Recent advances in generative AI, particularly in computer vision (CV), offer new opportunities to optimize workflows across industries, including logistics and manufacturing. However, many AI applications are limited by…

Object Detection

Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper

2026-02-26 · Hoan My Tran, Xin Wang, Wanying Ge, Xuechen Liu 외 arxiv

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector coul…