← Back to explorer

More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models

Evan Chen, Run-Jun Zhan, Yan-Bai Lin, Hung-Hsuan Chen · Mar 20, 2025 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 9, 2026, 6:46 AM

Recent

Extraction refreshed

Mar 13, 2026, 4:54 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases. This study introduces a novel evaluation framework to uncover gender biases in LLMs: using free-form storytelling to surface biases embedded within the models. A systematic analysis of ten prominent LLMs shows a consistent pattern of overrepresenting female characters across occupations, likely due to supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Paradoxically, despite this overrepresentation, the occupational gender distributions produced by these LLMs align more closely with human stereotypes than with real-world labor data. This highlights the challenge and importance of implementing balanced mitigation measures to promote fairness and prevent the establishment of potentially new biases. We release the prompts and LLM-generated stories at GitHub.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

Extraction confidence is 0.45 (below strong-reference threshold).
No explicit evaluation mode was extracted from available metadata.
No benchmark/dataset or metric anchors were extracted.

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction confidence is 0.45 (below strong-reference threshold).

Trust level

Low

Eval-Fit Score

5/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases.

Reported Metrics

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No metric anchors detected.

Evidence snippet: Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases.

Human Data Lens

Uses human feedback: Yes
Feedback types: None
Rater population: Unknown
Unit of annotation: Freeform
Expertise required: General
Extraction source: Persisted extraction

Evaluation Lens

Evaluation modes:
Agentic eval: None
Quality controls: Not reported
Confidence: 0.45
Flags: ambiguous

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

This study introduces a novel evaluation framework to uncover gender biases in LLMs: using free-form storytelling to surface biases embedded within the models. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Mar 13, 2026, 4:54 PM · Grounded in abstract + metadata only

Key Takeaways

This study introduces a novel evaluation framework to uncover gender biases in LLMs: using free-form storytelling to surface biases embedded within the models.
A systematic analysis of ten prominent LLMs shows a consistent pattern of overrepresenting female characters across occupations, likely due to supervised fine-tuning (SFT) and…

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Verify metric definitions before comparing against your eval pipeline.

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Extraction confidence is probabilistic and should be validated for critical decisions.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

This study introduces a novel evaluation framework to uncover gender biases in LLMs: using free-form storytelling to surface biases embedded within the models.
A systematic analysis of ten prominent LLMs shows a consistent pattern of overrepresenting female characters across occupations, likely due to supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF).
Paradoxically, despite this overrepresentation, the occupational gender distributions produced by these LLMs align more closely with human stereotypes than with real-world labor data.

Why It Matters For Eval

This study introduces a novel evaluation framework to uncover gender biases in LLMs: using free-form storytelling to surface biases embedded within the models.
A systematic analysis of ten prominent LLMs shows a consistent pattern of overrepresenting female characters across occupations, likely due to supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF).

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Gap: Evaluation mode is explicit

No clear evaluation mode extracted.
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Gap: Metric reporting is present

No metric terms extracted.

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Aligning Large Language Models with Searcher Preferences
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)
COMIC: Agentic Sketch Comedy Generation
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)
Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)
Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)
Emulating Clinician Cognition via Self-Evolving Deep Clinical Research
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)
IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)
Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)
Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CL, cs.AI)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote