LLM Generated Distribution-Based Prediction of US Electoral Results, Part I
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909378944172032 |
|---|---|
| author | Bradshaw, Caleb Miller, Caelen Warnick, Sean |
| author_facet | Bradshaw, Caleb Miller, Caelen Warnick, Sean |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03486 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM Generated Distribution-Based Prediction of US Electoral Results, Part I Bradshaw, Caleb Miller, Caelen Warnick, Sean Artificial Intelligence Computation and Language 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. |
| title | LLM Generated Distribution-Based Prediction of US Electoral Results, Part I |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2411.03486 |