Saved in:
Bibliographic Details
Main Author: Kunz, Jenny
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.12674
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929635088924672
author Kunz, Jenny
author_facet Kunz, Jenny
contents Smaller LLMs still face significant challenges even in medium-resourced languages, particularly when it comes to language-specific knowledge -- a problem not easily resolved with machine-translated data. In this case study on Icelandic, we aim to enhance the generation performance of an LLM by specialising it using unstructured text corpora. A key focus is on preventing interference with the models' capabilities of handling longer context during this adaptation. Through ablation studies using various parameter-efficient fine-tuning (PEFT) methods and setups, we find that increasing the number of trainable parameters leads to better and more robust language adaptation. LoRAs placed in the feed-forward layers and bottleneck adapters show promising results with sufficient parameters, while prefix tuning and (IA)3 are not suitable. Although improvements are consistent in 0-shot summarisation, some adapted models struggle with longer context lengths, an issue that can be mitigated by adapting only the final layers.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12674
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Train More Parameters But Mind Their Placement: Insights into Language Adaptation with PEFT
Kunz, Jenny
Computation and Language
Smaller LLMs still face significant challenges even in medium-resourced languages, particularly when it comes to language-specific knowledge -- a problem not easily resolved with machine-translated data. In this case study on Icelandic, we aim to enhance the generation performance of an LLM by specialising it using unstructured text corpora. A key focus is on preventing interference with the models' capabilities of handling longer context during this adaptation. Through ablation studies using various parameter-efficient fine-tuning (PEFT) methods and setups, we find that increasing the number of trainable parameters leads to better and more robust language adaptation. LoRAs placed in the feed-forward layers and bottleneck adapters show promising results with sufficient parameters, while prefix tuning and (IA)3 are not suitable. Although improvements are consistent in 0-shot summarisation, some adapted models struggle with longer context lengths, an issue that can be mitigated by adapting only the final layers.
title Train More Parameters But Mind Their Placement: Insights into Language Adaptation with PEFT
topic Computation and Language
url https://arxiv.org/abs/2412.12674