Cultural Biases of Large Language Models and Humans in Historical Interpretation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908918070902784 |
|---|---|
| author | Celli, Fabio Spathulas, Georgios |
| author_facet | Celli, Fabio Spathulas, Georgios |
| contents | This paper compares historical annotations by humans and Large Language Models. The findings reveal that both exhibit some cultural bias, but Large Language Models achieve a higher consensus on the interpretation of historical facts from short texts. While humans tend to disagree on the basis of their personal biases, Large Models disagree when they skip information or produce hallucinations. These findings have significant implications for digital humanities, enabling large-scale annotation and quantitative analysis of historical data. This offers new educational and research opportunities to explore historical interpretations from different Language Models, fostering critical thinking about bias. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02572 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cultural Biases of Large Language Models and Humans in Historical Interpretation Celli, Fabio Spathulas, Georgios Computation and Language This paper compares historical annotations by humans and Large Language Models. The findings reveal that both exhibit some cultural bias, but Large Language Models achieve a higher consensus on the interpretation of historical facts from short texts. While humans tend to disagree on the basis of their personal biases, Large Models disagree when they skip information or produce hallucinations. These findings have significant implications for digital humanities, enabling large-scale annotation and quantitative analysis of historical data. This offers new educational and research opportunities to explore historical interpretations from different Language Models, fostering critical thinking about bias. |
| title | Cultural Biases of Large Language Models and Humans in Historical Interpretation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.02572 |