Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910509156007936 |
|---|---|
| author | Zhou, Jingyan Hu, Minda Li, Junan Zhang, Xiaoying Wu, Xixin King, Irwin Meng, Helen |
| author_facet | Zhou, Jingyan Hu, Minda Li, Junan Zhang, Xiaoying Wu, Xixin King, Irwin Meng, Helen |
| contents | Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. These approaches have been criticized for overgeneralizing the moral stances of a limited group of annotators and lacking explainability. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research. The theory-guided top-down framework can incorporate various moral theories. Our experiments demonstrate the effectiveness of the proposed framework on datasets derived from moral theories. Furthermore, we show the alignment between different moral theories and existing morality datasets. Our analysis exhibits the potential and flaws in existing resources (models and datasets) in developing explainable moral judgment-making systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_15399 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? Zhou, Jingyan Hu, Minda Li, Junan Zhang, Xiaoying Wu, Xixin King, Irwin Meng, Helen Computation and Language Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. These approaches have been criticized for overgeneralizing the moral stances of a limited group of annotators and lacking explainability. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research. The theory-guided top-down framework can incorporate various moral theories. Our experiments demonstrate the effectiveness of the proposed framework on datasets derived from moral theories. Furthermore, we show the alignment between different moral theories and existing morality datasets. Our analysis exhibits the potential and flaws in existing resources (models and datasets) in developing explainable moral judgment-making systems. |
| title | Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2308.15399 |