Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.22232 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912454245613568 |
|---|---|
| author | Haller, Patrick Vamvas, Jannis Sennrich, Rico Jäger, Lena A. |
| author_facet | Haller, Patrick Vamvas, Jannis Sennrich, Rico Jäger, Lena A. |
| contents | A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruction-tuned models to their base versions. Experiments with LLMs of various sizes indicate that instruction tuning can indeed change the direction of bias. Furthermore, we observe a trend that larger models are able to leverage in-context examples more effectively, and generally exhibit smaller bias scores in QM. Data and code are publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22232 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging In-Context Learning for Political Bias Testing of LLMs Haller, Patrick Vamvas, Jannis Sennrich, Rico Jäger, Lena A. Computation and Language A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruction-tuned models to their base versions. Experiments with LLMs of various sizes indicate that instruction tuning can indeed change the direction of bias. Furthermore, we observe a trend that larger models are able to leverage in-context examples more effectively, and generally exhibit smaller bias scores in QM. Data and code are publicly available. |
| title | Leveraging In-Context Learning for Political Bias Testing of LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.22232 |