# LLM Generated Distribution-Based Prediction of US Electoral Results, Part I

arXiv: https://arxiv.org/abs/2411.03486 · HTML: https://mlsanity.com/paper/2411.03486/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 6 of 6)

- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [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)
- [Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information](https://mlsanity.com/paper/2402.18144/) (2024)
- [An Investigation of Prompt Variations for Zero-shot LLM-based Rankers](https://mlsanity.com/paper/2406.14117/) (2024)
- [Can LLMs Help Predict Elections? (Counter)Evidence from the World's Largest Democracy](https://mlsanity.com/paper/2405.07828/) (2024)

## Built on by (most cited first, 3 of 3)

- [Characterizing the ability of LLMs to recapitulate Americans' distributional responses to public opinion polling questions across political issues](https://mlsanity.com/paper/2603.20229/) (2026)
- [Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models](https://mlsanity.com/paper/2506.11798/) (2025)
- [FlockVote: LLM-Empowered Agent-Based Modeling for Simulating U.S. Presidential Elections](https://mlsanity.com/paper/2512.05982/) (2025)

## Abstract (arXiv)

This paper introduces distribution-based prediction, a novel approach to using Large Language Models (LLMs) as predictive tools by interpreting output token probabilities as distributions representing the models' learned representation of the world. This distribution-based nature offers an alternative perspective for analyzing algorithmic fidelity, complementing the approach used in silicon sampling. We demonstrate the use of distribution-based prediction in the context of recent United States presidential election, showing that this method can be used to determine task specific bias, prompt noise, and algorithmic fidelity. This approach has significant implications for assessing the reliability and increasing transparency of LLM-based predictions across various domains.