# Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models

Source: [Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models](<https://www.sota2.com/research/paper/68fa758d1e209131cea68938>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T04:59:09.974Z

Authors: Minki Kang, Sung Ju Hwang, Gibbeum Lee, Jaewoong Cho

Published: 2024-11-01T15:47:05.000Z

## Abstract

As Large Language Models (LLMs) are increasingly deployed in specialized domains with continuously evolving knowledge, the need for timely and precise knowledge injection has become essential. Fine-tuning with paraphrased data is a common approach to enhance knowledge injection, yet it faces two significant challenges: high computational costs due to repetitive external model usage and limited sample diversity. To this end, we introduce LaPael, a latent-level paraphrasing method that applies input-dependent noise to early LLM layers. This approach enables diverse and semantically consistent augmentations directly within the model. Furthermore, it eliminates the recurring costs of paraphrase generation for each knowledge update. Our extensive experiments on question-answering benchmarks demonstrate that LaPael improves knowledge injection over standard fine-tuning and existing noise-based approaches. Additionally, combining LaPael with data-level paraphrasing further enhances performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.00686>)

[PDF](<https://arxiv.org/pdf/2411.00686.pdf>)
