Improving the Distributional Alignment of LLMs using Supervision
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914492686794752 |
|---|---|
| author | Kambhatla, Gauri Gautam, Sanjana Zhang, Angela Liu, Alex Srinivasan, Ravi Li, Junyi Jessy Lease, Matthew |
| author_facet | Kambhatla, Gauri Gautam, Sanjana Zhang, Angela Liu, Alex Srinivasan, Ravi Li, Junyi Jessy Lease, Matthew |
| contents | The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more consistently improve the alignment of LLM-generated distributions with diverse population groups, as measured across three datasets spanning public health, public opinion, and values and beliefs. Beyond evaluating average alignment, we also report how alignment varies across specific groups. Our broad findings provide insights into the distributional alignment of LLM generations with diverse populations. By conducting evaluation over many LLMs and prompting strategies, we provide a benchmark to stimulate future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00439 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving the Distributional Alignment of LLMs using Supervision Kambhatla, Gauri Gautam, Sanjana Zhang, Angela Liu, Alex Srinivasan, Ravi Li, Junyi Jessy Lease, Matthew Computation and Language The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more consistently improve the alignment of LLM-generated distributions with diverse population groups, as measured across three datasets spanning public health, public opinion, and values and beliefs. Beyond evaluating average alignment, we also report how alignment varies across specific groups. Our broad findings provide insights into the distributional alignment of LLM generations with diverse populations. By conducting evaluation over many LLMs and prompting strategies, we provide a benchmark to stimulate future research. |
| title | Improving the Distributional Alignment of LLMs using Supervision |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.00439 |