Building Interpretable Models for Moral Decision-Making
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911421674029056 |
|---|---|
| author | Goel, Mayank Das, Aritra Chopra, Paras |
| author_facet | Goel, Mayank Das, Aritra Chopra, Paras |
| contents | We build a custom transformer model to study how neural networks make moral decisions on trolley-style dilemmas. The model processes structured scenarios using embeddings that encode who is affected, how many people, and which outcome they belong to. Our 2-layer architecture achieves 77% accuracy on Moral Machine data while remaining small enough for detailed analysis. We use different interpretability techniques to uncover how moral reasoning distributes across the network, demonstrating that biases localize to distinct computational stages among other findings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03351 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Building Interpretable Models for Moral Decision-Making Goel, Mayank Das, Aritra Chopra, Paras Artificial Intelligence Computers and Society Machine Learning We build a custom transformer model to study how neural networks make moral decisions on trolley-style dilemmas. The model processes structured scenarios using embeddings that encode who is affected, how many people, and which outcome they belong to. Our 2-layer architecture achieves 77% accuracy on Moral Machine data while remaining small enough for detailed analysis. We use different interpretability techniques to uncover how moral reasoning distributes across the network, demonstrating that biases localize to distinct computational stages among other findings. |
| title | Building Interpretable Models for Moral Decision-Making |
| topic | Artificial Intelligence Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2602.03351 |