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

TL;DR

This paper proposes a method to validate algorithmic decisions about humans by comparing input representations with self-descriptions, introducing a new benchmark dataset for evaluating representation fidelity in loan decisions.

Contribution

It introduces the concept of representation fidelity, a typology of mismatches, and provides the first benchmark dataset for assessing decision validity through self-descriptions.

Findings

Identifies key types of representation mismatches.

Develops a metric to quantify discrepancies.

Provides a large annotated dataset for evaluation.

Abstract

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.