Skip to content
Back to skills

Adapting A Language Model While Preserving Its General Knowledge

ASecurity

**arXiv ID:** 2301.08986 **Authors:** Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu **Published:** 2023-01-21T17:57:53Z **Abstract:** Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that end-tasks in the domain can give improved performances. However, existing DA-training methods are in some sense blind as they ...

  • 3 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added September 11, 2026
toolsperformance

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill adapting-a-language-model-while-preserving-its-general-knowledge --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adapting A Language Model While Preserving Its General Knowledge?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Adapting A Language Model While Preserving Its General Knowledge
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-adapting-a-language-model-while-preserving-its-gen/badge)](https://www.skillsdirectory.com/skills/hiyenwong-adapting-a-language-model-while-preserving-its-gen)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Adapting a Language Model While Preserving its General Knowledge

**arXiv ID:** 2301.08986
**Authors:** Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu
**Published:** 2023-01-21T17:57:53Z
**Abstract:**
Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that end-tasks in the domain can give improved performances. However, existing DA-training methods are in some sense blind as they do not explicitly identify what knowledge in the LM should be preserved and what should be changed by the domain corpus. This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge. Experimental results will demonstrate the effectiveness of the proposed approach.

## Skill Description

This skill is generated from the arXiv paper: Adapting a Language Model While Preserving its General Knowledge (2301.08986).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2301.08986](http://arxiv.org/abs/2301.08986v1)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.