CLDec 17, 2024

Train More Parameters But Mind Their Placement: Insights into Language Adaptation with PEFT

arXiv:2412.12674v112 citationsh-index: 2NoDaLiDa/Baltic-HLT
Originality Incremental advance
AI Analysis

This addresses language-specific knowledge gaps for smaller LLMs in medium-resourced languages, but it is incremental as it builds on existing PEFT techniques.

The study tackled improving language adaptation for smaller LLMs in medium-resourced languages like Icelandic by using parameter-efficient fine-tuning (PEFT) methods, finding that increasing trainable parameters leads to better and more robust performance, with LoRAs in feed-forward layers and bottleneck adapters showing promising results.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes