mirror of
https://github.com/wassname/AntiPaSTO.git
synced 2026-09-21 12:30:21 +08:00
38 lines
1.1 KiB
YAML
38 lines
1.1 KiB
YAML
# This CITATION.cff file was generated with cffinit.
|
|
# Visit https://bit.ly/cffinit to generate yours today!
|
|
|
|
cff-version: 1.2.0
|
|
title: "AntiPaSTO: Self-Supervised Steering of Moral Reasoning"
|
|
message: "If you use this software, please cite it as below."
|
|
type: software
|
|
authors:
|
|
- given-names: Michael J
|
|
family-names: Clark
|
|
orcid: "https://orcid.org/0009-0008-9023-8720"
|
|
repository-code: "https://github.com/wassname/AntiPaSTO"
|
|
url: "https://github.com/wassname/AntiPaSTO"
|
|
license: MIT
|
|
version: "0.5.0"
|
|
date-released: "2026-01-13"
|
|
keywords:
|
|
- machine-learning
|
|
- llm
|
|
- steering
|
|
- alignment
|
|
- moral-reasoning
|
|
- pytorch
|
|
- peft
|
|
abstract: >-
|
|
Self-supervised steering of moral reasoning via antiparallel
|
|
subspace training. Gradient-based steering in SVD transformation
|
|
space, trained on internal representations without preference labels.
|
|
preferred-citation:
|
|
type: article
|
|
authors:
|
|
- given-names: Michael J
|
|
family-names: Clark
|
|
orcid: "https://orcid.org/0009-0008-9023-8720"
|
|
title: "AntiPaSTO: Self-Supervised Steering of Moral Reasoning"
|
|
year: 2026
|
|
# doi: "10.48550/arXiv.2501.XXXXX" # Uncomment when arXiv ID available
|