Saved in:
Bibliographic Details
Main Authors: Zhu, Wenhong, Zhang, Weinan, Wang, Rui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.04346
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908756122533888
author Zhu, Wenhong
Zhang, Weinan
Wang, Rui
author_facet Zhu, Wenhong
Zhang, Weinan
Wang, Rui
contents Post-training alignment has increasingly become a crucial factor in enhancing the usability of language models (LMs). However, the strength of alignment varies depending on individual preferences. This paper proposes a method to incorporate alignment control into a single model, referred to as CLM. This approach adds one identity layer preceding the initial layers and performs preference learning only on this layer to map unaligned input token embeddings into the aligned space. Experimental results demonstrate that this efficient fine-tuning method performs comparable to full fine-tuning. During inference, the input embeddings are processed through the aligned and unaligned layers, which are then merged through the interpolation coefficient. By controlling this parameter, the alignment exhibits a clear interpolation and extrapolation phenomenon.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adding Alignment Control to Language Models
Zhu, Wenhong
Zhang, Weinan
Wang, Rui
Computation and Language
Post-training alignment has increasingly become a crucial factor in enhancing the usability of language models (LMs). However, the strength of alignment varies depending on individual preferences. This paper proposes a method to incorporate alignment control into a single model, referred to as CLM. This approach adds one identity layer preceding the initial layers and performs preference learning only on this layer to map unaligned input token embeddings into the aligned space. Experimental results demonstrate that this efficient fine-tuning method performs comparable to full fine-tuning. During inference, the input embeddings are processed through the aligned and unaligned layers, which are then merged through the interpolation coefficient. By controlling this parameter, the alignment exhibits a clear interpolation and extrapolation phenomenon.
title Adding Alignment Control to Language Models
topic Computation and Language
url https://arxiv.org/abs/2503.04346