Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa

• URL: http://arxiv.org/abs/2605.25816v1
• Date: Mon, 25 May 2026 13:12:42 GMT
• Title: Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa
• Abstract summary: PII detection systems are frequently trained within narrow source or domain boundaries, limiting coverage when deployed on heterogeneous text.<n>We study model fine-tuning on a corrected multi-source PIIBench preparation spanning 82 retained entity types across ten source datasets.<n>We evaluate three DeBERTa-based approaches: direct token classification fine-tuning, a source-conditioned hierarchical model (SC+H), and a three-phase curriculum extension (SC+H+Curr)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Personally identifiable information (PII) detection systems are frequently trained within narrow source or domain boundaries, limiting coverage when deployed on heterogeneous text. We study model fine-tuning on a corrected multi-source PIIBench preparation spanning 82 retained entity types across ten source datasets. We evaluate three DeBERTa-based approaches: direct token classification fine-tuning, a source-conditioned hierarchical model (SC+H), and a three-phase curriculum extension (SC+H+Curr). Against eight published comparator systems on a reproducible 5,000-record held-out subset (test_5k), direct fine-tuned DeBERTa achieves F1 0.6476, while SC+H and the curriculum variant achieve 0.5899 and 0.2772 respectively; the strongest published comparator reaches only 0.1723. Because validation initially favoured SC+H, we perform a final streamed evaluation on the complete 100,002-record held-out split. Direct fine-tuning remains superior, achieving F1 0.6455 versus 0.5894 for SC+H. Entity-level analysis shows that direct fine tuning wins 54 of 82 fine entity types and all ten coarse groups by support-weighted entity F1, while SC+H retains localised advantages on 28 types. The results indicate that diverse task-specific training data and a simple weighted cross-entropy objective contribute more to broad-coverage PII detection than the tested architectural and curriculum complexity.

Related papers

• Coarse composition suffices: tabular in-context learning for multi-activity antimicrobial peptide profiling [2.571440349338848]
  We show that a simple, sequence-only pipeline can match and surpass multimodal, structure-conditioned deep models.<n>On ESCAPE (82,359 peptides; five labels), a label-powerset TabPFN model achieves mAP-5 = 77.8%, improving on the previously best reported 72.1%.
  arXiv  Detail & Related papers  (2026-08-31T06:50:09Z)
• Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis [48.83701310501069]
  We introduce a MinHash-based similarity scheduling framework that constructs a progressive curriculum over neural architecture code for neural architecture search (NAS)<n>We evaluate the framework on OlympicCoder-7B within the LEMUR benchmark on CIFAR-10 image classification.<n>We report a cross-dataset transfer observation on SVHN, where direct base-model generation without curriculum yields 27% peak SR at substantially lower accuracy (60.5%) than the CIFAR-10 equivalent.
  arXiv  Detail & Related papers  (2026-07-13T14:14:30Z)
• Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems [47.027290803102666]
  Normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes.<n>We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering.<n>We evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration.
  arXiv  Detail & Related papers  (2026-07-07T10:10:00Z)
• ATLAS: All-round Testing of Long-context Abilities across Scales [42.83200405769639]
  ATLAS is a benchmarking framework that redefines long-context evaluation as length-dependent capability profiling.<n> ATLAS contributes three methodological principles: (i) a layered taxonomy separating foundational operations from application workloads so failures can be attributed, (ii) length-aware AUC scoring that integrates score-length curves over a fixed 8K-1M grid, replacing single-point metrics with full degradation profiles, and (iii) ATLAScore, a harmonic-mean aggregate over taxonomy categories that penalizes imbalanced profiles.
  arXiv  Detail & Related papers  (2026-05-27T07:33:47Z)
• The autoPET3 Challenge: Automated Lesion Segmentation in Whole-Body PET/CT $\unicode{x2013}$ Multitracer Multicenter Generalization [67.92281859568168]
  We report the design and results of the third autoPET challenge (MICCAI 2024)<n>It benchmarked automated lesion segmentation in whole-body PET/CT under a compositional generalization setting.<n>The top-ranked algorithm achieved a mean DSC of 0.66, FNV of 3.18 mL, and FPV of 2.78 mL across all four test conditions.
  arXiv  Detail & Related papers  (2026-05-07T07:07:09Z)
• Donor-Aware scRNA-seq Benchmarks for IBD Classification [0.0]
  Donor-level disease classification from single-cell RNA sequencing (scRNA-seq) requires strict donor-aware cross-validation.<n>We present a donor-aware benchmark evaluating three feature representations across two independent IBD atlases.
  arXiv  Detail & Related papers  (2026-05-05T02:13:43Z)
• Paired-CSLiDAR: Height-Stratified Registration for Cross-Source Aerial-Ground LiDAR Pose Refinement [46.13526676100776]
  We introduce Paired-CSLiDAR, a cross-source aerial-ground LiDAR benchmark for single-scan pose refinement.<n>The benchmark contains 12,683 ground-aerial pairs across 6 evaluation sites.<n>We propose Residual-Guided Stratified Registration (RGSR), a training-free, geometry-only refinement pipeline.
  arXiv  Detail & Related papers  (2026-05-01T13:14:20Z)
• Quantum-Inspired Geometric Classification with Correlation Group Structures and VQC Decision Modeling [0.5039813366558307]
  We propose a geometry-driven quantum-inspired classification framework that integrates Correlation Group Structures (CGR), compact SWAP-test-based overlap estimation, and selective variational quantum decision modelling.<n>CGR organizes features into anchor-centered correlation neighbourhoods, generating nonlinear, correlation-weighted representations.<n>On the Credit Card Fraud dataset (0.17% prevalence), the Delta + VQC pipeline achieves approximately 0.85 minority recall at an alert rate of approximately 1.31%, with ROC-AUC 0.9249 and PR-AUC 0.3251 under full-dataset evaluation.
  arXiv  Detail & Related papers  (2026-04-02T11:50:29Z)
• FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation [63.7829089874007]
  This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation.<n>FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images.<n> Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2.
  arXiv  Detail & Related papers  (2026-01-22T01:34:39Z)
• A Comprehensive Forecasting-Based Framework for Time Series Anomaly Detection: Benchmarking on the Numenta Anomaly Benchmark (NAB) [0.0]
  Time series anomaly detection is critical for modern digital infrastructures.<n>We present a forecasting-based framework unifying classical methods with deep learning architectures.<n>We conduct the first complete evaluation on the Numenta Anomaly Benchmark.
  arXiv  Detail & Related papers  (2025-10-13T08:31:42Z)
• Segment-and-Classify: ROI-Guided Generalizable Contrast Phase Classification in CT Using XGBoost [7.689389068258514]
  This study utilized three public CT datasets from separate institutions.<n>The phase prediction model was trained on the WAW-TACE dataset and validated on the VinDr-Multiphase and C4KC-KiTS datasets.
  arXiv  Detail & Related papers  (2025-01-23T20:01:33Z)
• Decorrelating Structure via Adapters Makes Ensemble Learning Practical for Semi-supervised Learning [50.868594148443215]
  In computer vision, traditional ensemble learning methods exhibit either a low training efficiency or the limited performance. We propose a lightweight, loss-function-free, and architecture-agnostic ensemble learning by the Decorrelating Structure via Adapters (DSA) for various visual tasks.
  arXiv  Detail & Related papers  (2024-08-08T01:31:38Z)
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection [85.53263670166304]
  One-stage detector basically formulates object detection as dense classification and localization. Recent trend for one-stage detectors is to introduce an individual prediction branch to estimate the quality of localization. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization.
  arXiv  Detail & Related papers  (2020-06-08T07:24:33Z)

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.