mlsanityData to 7 Oct 2026

Hypernetworks for Perspectivist Adaptation

arXiv 2510.13259 ↗First posted 15 Oct 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The task of perspective-aware classification introduces a bottleneck in terms of parametric efficiency that did not get enough recognition in existing studies. In this article, we aim to address this issue by applying an existing architecture, the hypernetwork+adapters combination, to perspectivist classification. Ultimately, we arrive at a solution that can compete with specialized models in adopting user perspectives on hate speech and toxicity detection, while also making use of considerably fewer parameters. Our solution is architecture-agnostic and can be applied to a wide range of base models out of the box.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 15 Oct 2025.

Builds on

25 of 44 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  7. 2021Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotationscited by 306
  8. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 278
  9. 2021Toward a Perspectivist Turn in Ground Truthing for Predictive Computingcited by 129
  10. 2017Deep learning from crowdscited by 105
  11. 2021Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreementcited by 71
  12. 2022HyperPrompt: Prompt-based Task-Conditioning of Transformerscited by 67
13 more
  1. 2021Designing Toxic Content Classification for a Diversity of Perspectivescited by 63
  2. 2023SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)cited by 52
  3. 2025Text-to-LoRA: Instant Transformer Adaptioncited by 50
  4. 2023You Are What You Annotate: Towards Better Models through Annotator Representationscited by 40
  5. 2021Whose Opinions Matter? Perspective-aware Models to Identify Opinions of Hate Speech Victims in Abusive Language Detectioncited by 38
  6. 2024The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labelscited by 37
  7. 2025Value Profiles for Encoding Human Variationcited by 29
  8. 2023Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Taskscited by 28
  9. 2022Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfercited by 22
  10. 2023ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variationcited by 17
  11. 2023Incorporating Worker Perspectives into MTurk Annotation Practices for NLPcited by 17
  12. 2024PEFT-U: Parameter-Efficient Fine-Tuning for User Personalizationcited by 11
  13. 2024Corpus Considerations for Annotator Modeling and Scalingcited by 8

Built on by

Not cited yet.