Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models

Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi

Abstract

As Large Language Models (LLMs) increasingly power decision-making systems across critical domains, understanding and mitigating their biases becomes essential for responsible AI deployment. Although bias assessment frameworks have proliferated for attributes such as race and gender, socioeconomic status bias remains significantly underexplored despite its widespread implications in the real world. We introduce SocioEval, a template-based framework for systematically evaluating socioeconomic bias in foundation models through decision-making tasks. Our hierarchical framework encompasses 8 themes and 18 topics, generating 240 prompts across 6 class-pair combinations. We evaluated 13 frontier LLMs on 3,120 responses using a rigorous three-stage annotation protocol, revealing substantial variation in bias rates (0.42\%-33.75\%). Our findings demonstrate that bias manifests differently across themes lifestyle judgments show 10$\times$ higher bias than education-related decisions and that deployment safeguards effectively prevent explicit discrimination but show brittleness to domain-specific stereotypes. SocioEval provides a scalable, extensible foundation for auditing class-based bias in language models.

SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models

Abstract

As Large Language Models (LLMs) increasingly power decision-making systems across critical domains, understanding and mitigating their biases becomes essential for responsible AI deployment. Although bias assessment frameworks have proliferated for attributes such as race and gender, socioeconomic status bias remains significantly underexplored despite its widespread implications in the real world. We introduce SocioEval, a template-based framework for systematically evaluating socioeconomic bias in foundation models through decision-making tasks. Our hierarchical framework encompasses 8 themes and 18 topics, generating 240 prompts across 6 class-pair combinations. We evaluated 13 frontier LLMs on 3,120 responses using a rigorous three-stage annotation protocol, revealing substantial variation in bias rates (0.42\%-33.75\%). Our findings demonstrate that bias manifests differently across themes lifestyle judgments show 10 higher bias than education-related decisions and that deployment safeguards effectively prevent explicit discrimination but show brittleness to domain-specific stereotypes. SocioEval provides a scalable, extensible foundation for auditing class-based bias in language models.

Paper Structure

This paper contains 21 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Bias Evaluation in Language Models
  4. Socioeconomic Bias in AI Systems
  5. AI Governance and Fairness
  6. Methodology
  7. Task Design
  8. Hierarchical Evaluation Structure
  9. Templatization and Dataset Curation
  10. Evaluation Protocol
  11. Models Evaluated
  12. Results
  13. Cross-Model Bias Patterns (RQ1)
  14. Theme and Topic Variation (RQ2)
  15. Response Strategies and Safeguards (RQ3)
  16. ...and 6 more sections

Figures (5)

  • Figure 1: Overview of the SocioEval framework. (Left) The hierarchical data structure comprises 8 comprehensive themes, 18 fine-grained topics, 4 distinct class identities, and 6 class pair combinations. (Right) A three-stage evaluation protocol applied to 3,120 model responses, consisting of contextual review (prompt-response analysis and reasoning patterns), classification (biased or unbiased), and quality assurance (validation and agreement checks).
  • Figure 2: Bias rates across 13 frontier LLMs. Anthropic models show lowest bias rates, while Mistral models exhibit highest. Error bars represent 95% confidence intervals.
  • Figure 3: Bias rates by theme and class pair. Lifestyle themes show highest bias, while education-related themes show lowest. Extreme class pairs (upper vs. working) elicit more bias than adjacent pairs.
  • Figure 4: Distribution of response strategies across models. Anthropic models show high refusal rates; open-source models show varied patterns. Class preference is the most common biased response type.
  • Figure 5: Distribution of fine-grained response classifications across 13 models. The six categories reveal distinct patterns: Anthropic models show high refusal rates, while models with high bias rates predominantly exhibit class preference. This visualization demonstrates the value of granular classification in understanding model behavior.