arXiv Open Access 2026

CounterMoral: Editing Morals in Language Models

Michael Ripa Jim Davies
Lihat Sumber

Abstrak

Recent advancements in language model technology have significantly enhanced the ability to edit factual information. Yet, the modification of moral judgments, a crucial aspect of aligning models with human values, has garnered less attention. In this work, we introduce CounterMoral, a benchmark dataset crafted to assess how well current model editing techniques modify moral judgments across diverse ethical frameworks. We apply various editing techniques to multiple language models and evaluate their performance. Our findings contribute to the evaluation of language models designed to be ethical.

Topik & Kata Kunci

Penulis (2)

M

Michael Ripa

J

Jim Davies

Format Sitasi

Ripa, M., Davies, J. (2026). CounterMoral: Editing Morals in Language Models. https://arxiv.org/abs/2603.27338

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓