cs.CLNov 14, 2026

When Does Label-Free Deconfounding of Document Embeddings Work?

Authors: Anna Kiepura, Yingqiang Gao, Elliott Ash, Yu Fan

Organizations: ETH Zurich · Department of Computational Linguistics, University of Zurich · Department of Computational Linguistics University of Zurich · The University of Hong Kong

Abstract

Document embeddings encode spurious attributes that can distort semantic comparisons; yet supervised erasure requires metadata that is often unavailable. We systematically investigate label-free deconfounding across corpora and embedding models. Our results show that label-free methods improve semantic utility over unprocessed embeddings, while simple geometric approaches recover much of the supervised benefit, sometimes matching metadata-supervised erasure in linear confounder recoverability and semantic utility. We identify two distinct causes of ineffective erasure: poor proxy-confounder alignment and insufficient intervention coverage. Crucially, confounder recoverability and semantic utility are distinct dimensions of deconfounding success: utility can improve despite residual confounder information, while stronger suppression does not necessarily improve utility. Moreover, reduced linear recoverability can coexist with substantial nonlinear recoverability. Together, these findings distinguish confounder discovery from intervention effectiveness and highlight the importance of evaluating nuisance suppression alongside semantic preservation.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. FLARE: Task-agnostic embedding model evaluation through a normalization process

    Apr 19, 2026Jingzhou Jiang, Yixuan Tang, Yi Yang +1Text Embedding EvaluationText Embedding Models

  2. Principled Nonlinear Concept Erasure and Steering

    Oct 23, 2026Idan Simai, Shauli Ravfogel, Uri ShahamConcept ErasurePrivacy-Preserving Representation Learning

  3. Hidden not Deleted: How Networks Suppress Entangled Features

    Sep 23, 2026Akash Samanta, Manish Pratap Singh, Debasis ChaudhuriFeature SuperpositionMechanistic Interpretability