Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.18027 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915688047706112 |
|---|---|
| author | Chakrabarti, Samidh Willner, David Klyman, Kevin Saade, Tiffany Capstick, Emily Nong, Sabina |
| author_facet | Chakrabarti, Samidh Willner, David Klyman, Kevin Saade, Tiffany Capstick, Emily Nong, Sabina |
| contents | This paper details the methodology behind CoPE, a policy-steerable small language model capable of fast and accurate content labeling. We present a novel training curricula called Contradictory Example Training that enables the model to learn policy interpretation rather than mere policy memorization. We also present a novel method for generating content policies, called Binocular Labeling, which enables rapid construction of unambiguous training datasets. When evaluated across seven different harm areas, CoPE exhibits equal or superior accuracy to frontier models at only 1% of their size. We openly release a 9 billion parameter version of the model that can be run on a single consumer-grade GPU. Models like CoPE represent a paradigm shift for classifier systems. By turning an ML task into a policy writing task, CoPE opens up new design possibilities for the governance of online platforms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_18027 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoPE: A Small Language Model for Steerable and Scalable Content Labeling Chakrabarti, Samidh Willner, David Klyman, Kevin Saade, Tiffany Capstick, Emily Nong, Sabina Computation and Language Computers and Society Social and Information Networks I.2.7 This paper details the methodology behind CoPE, a policy-steerable small language model capable of fast and accurate content labeling. We present a novel training curricula called Contradictory Example Training that enables the model to learn policy interpretation rather than mere policy memorization. We also present a novel method for generating content policies, called Binocular Labeling, which enables rapid construction of unambiguous training datasets. When evaluated across seven different harm areas, CoPE exhibits equal or superior accuracy to frontier models at only 1% of their size. We openly release a 9 billion parameter version of the model that can be run on a single consumer-grade GPU. Models like CoPE represent a paradigm shift for classifier systems. By turning an ML task into a policy writing task, CoPE opens up new design possibilities for the governance of online platforms. |
| title | CoPE: A Small Language Model for Steerable and Scalable Content Labeling |
| topic | Computation and Language Computers and Society Social and Information Networks I.2.7 |
| url | https://arxiv.org/abs/2512.18027 |