mlsanityData to 7 Oct 2026

Representation Fidelity:Auditing Algorithmic Decisions About Humans Using Self-Descriptions

arXiv 2603.05136 ↗First posted 5 Mar 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new dimension for validating algorithmic decisions about humans by measuring the fidelity of their representations. Representation Fidelity measures if decisions about a person rest on reasonable grounds. We propose to operationalize this notion by measuring the distance between two representations of the same person: (1) an externally prescribed input representation on which the decision is based, and (2) a self-description provided by the human subject of the decision, used solely to validate the input representation. We examine the nature of discrepancies between these representations, how such discrepancies can be quantified, and derive a generic typology of representation mismatches that determine the degree of representation fidelity. We further present the first benchmark for evaluating representation fidelity based on a dataset of loan-granting decisions. Our Loan-Granting Self-Representations Corpus 2025 consists of a large corpus of 30 000 synthetic natural language self-descriptions derived from corresponding representations of applicants in the German Credit Dataset, along with expert annotations of representation mismatches between each pair of representations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 59 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

23 of 59 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  7. 2018Datasheets for Datasetscited by 1,371
  8. 2019Measurement and Fairnesscited by 299
  9. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 192
  10. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  11. 2022TEACH: Temporal Action Composition for 3D Humanscited by 173
  12. 2023Getting aligned on representational alignmentcited by 142
11 more
  1. 2020Outcome Indistinguishabilitycited by 74
  2. 2018Online Learning with an Unknown Fairness Metriccited by 61
  3. 2018Fairness Through Computationally-Bounded Awarenesscited by 55
  4. 2018Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Predictioncited by 35
  5. 2023Difficult Lessons on Social Prediction from Wisconsin Public Schoolscited by 35
  6. 2018Probably Approximately Metric-Fair Learningcited by 29
  7. 2023Taxonomizing and Measuring Representational Harms: A Look at Image Taggingcited by 24
  8. 2022Subverting machines, fluctuating identities: Re-learning human categorizationcited by 10
  9. 2025Taxonomizing Representational Harms using Speech Act Theorycited by 7
  10. 2025Embedding Atlas: Low-Friction, Interactive Embedding Visualizationcited by 7
  11. 2025Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairnesscited by 2

Built on by

Not cited yet.