Evaluating and Aligning Human Economic Risk Preferences in LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908536281235456 |
|---|---|
| author | Liu, Jiaxin Tang, Yixuan Yang, Yi Tam, Kar Yan |
| author_facet | Liu, Jiaxin Tang, Yixuan Yang, Yi Tam, Kar Yan |
| contents | Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk preferences consistent with human expectations across different personas. Specifically, we assess whether LLM-generated responses reflect appropriate levels of risk aversion or risk-seeking behavior based on individual's persona. Our results reveal that while LLMs make reasonable decisions in simplified, personalized risk contexts, their performance declines in more complex economic decision-making tasks. To address this, we propose an alignment method designed to enhance LLM adherence to persona-specific risk preferences. Our approach improves the economic rationality of LLMs in risk-related applications, offering a step toward more human-aligned AI decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06646 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating and Aligning Human Economic Risk Preferences in LLMs Liu, Jiaxin Tang, Yixuan Yang, Yi Tam, Kar Yan General Economics Economics Computation and Language Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk preferences consistent with human expectations across different personas. Specifically, we assess whether LLM-generated responses reflect appropriate levels of risk aversion or risk-seeking behavior based on individual's persona. Our results reveal that while LLMs make reasonable decisions in simplified, personalized risk contexts, their performance declines in more complex economic decision-making tasks. To address this, we propose an alignment method designed to enhance LLM adherence to persona-specific risk preferences. Our approach improves the economic rationality of LLMs in risk-related applications, offering a step toward more human-aligned AI decision-making. |
| title | Evaluating and Aligning Human Economic Risk Preferences in LLMs |
| topic | General Economics Economics Computation and Language |
| url | https://arxiv.org/abs/2503.06646 |