# Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs

arXiv: https://arxiv.org/abs/2311.09730 · HTML: https://mlsanity.com/paper/2311.09730/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting](https://mlsanity.com/paper/2309.07034/) (2023)
- [Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark](https://mlsanity.com/paper/2305.14938/) (2023)
- [When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset](https://mlsanity.com/paper/2306.06826/) (2023)
- [From task structures to world models: What do LLMs know?](https://mlsanity.com/paper/2310.04276/) (2023)
- [Exploring the psychology of LLMs' Moral and Legal Reasoning](https://mlsanity.com/paper/2308.01264/) (2023)

## Built on by (most cited first, 30 of 36)

- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations](https://mlsanity.com/paper/2601.17087/) (2026)
- [Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions](https://mlsanity.com/paper/2502.20897/) (2025)
- [MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms](https://mlsanity.com/paper/2402.14154/) (2024)
- [Creative Preference Optimization](https://mlsanity.com/paper/2505.14442/) (2025)
- [Annotation alignment: Comparing LLM and human annotations of conversational safety](https://mlsanity.com/paper/2406.06369/) (2024)
- [Personas with Attitudes: Controlling LLMs for Diverse Data Annotation](https://mlsanity.com/paper/2410.11745/) (2024)
- [Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification](https://mlsanity.com/paper/2510.11408/) (2025)
- [Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models](https://mlsanity.com/paper/2405.14555/) (2024)
- [Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives](https://mlsanity.com/paper/2508.02853/) (2025)
- [Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents](https://mlsanity.com/paper/2602.18462/) (2026)
- [Are Large Language Models Chameleons? An Attempt to Simulate Social Surveys](https://mlsanity.com/paper/2405.19323/) (2024)
- [Evaluating how LLM annotations represent diverse views on contentious topics](https://mlsanity.com/paper/2503.23243/) (2025)
- [Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models](https://mlsanity.com/paper/2402.17226/) (2024)
- [Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation](https://mlsanity.com/paper/2401.16558/) (2024)
- [The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum](https://mlsanity.com/paper/2508.17164/) (2025)
- [Improving the Distributional Alignment of LLMs using Supervision](https://mlsanity.com/paper/2507.00439/) (2025)
- [Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?](https://mlsanity.com/paper/2511.21218/) (2025)
- [Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication](https://mlsanity.com/paper/2501.06826/) (2025)
- [Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks](https://mlsanity.com/paper/2603.21404/) (2026)
- [From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?](https://mlsanity.com/paper/2604.17968/) (2026)
- [Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation](https://mlsanity.com/paper/2605.06318/) (2026)
- [Musical ethnocentrism in Large Language Models](https://mlsanity.com/paper/2501.13720/) (2025)
- [Disambiguation of Emotion Annotations by Contextualizing Events in Plausible Narratives](https://mlsanity.com/paper/2508.09954/) (2025)
- [DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning](https://mlsanity.com/paper/2509.09524/) (2025)
- [Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making](https://mlsanity.com/paper/2602.11924/) (2026)
- [Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP](https://mlsanity.com/paper/2603.28351/) (2026)
- [When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection](https://mlsanity.com/paper/2605.27313/) (2026)
- [Demographic Prompting at Scale: When More Attributes Hurt LLM--Human Agreement](https://mlsanity.com/paper/2607.10590/) (2026)

## Abstract (arXiv)

Human judgments are inherently subjective and are actively affected by personal traits such as gender and ethnicity. While Large Language Models (LLMs) are widely used to simulate human responses across diverse contexts, their ability to account for demographic differences in subjective tasks remains uncertain. In this study, leveraging the POPQUORN dataset, we evaluate nine popular LLMs on their ability to understand demographic differences in two subjective judgment tasks: politeness and offensiveness. We find that in zero-shot settings, most models' predictions for both tasks align more closely with labels from White participants than those from Asian or Black participants, while only a minor gender bias favoring women appears in the politeness task. Furthermore, sociodemographic prompting does not consistently improve and, in some cases, worsens LLMs' ability to perceive language from specific sub-populations. These findings highlight potential demographic biases in LLMs when performing subjective judgment tasks and underscore the limitations of sociodemographic prompting as a strategy to achieve pluralistic alignment. Code and data are available at: https://github.com/Jiaxin-Pei/LLM-as-Subjective-Judge.