Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910517284569088 |
|---|---|
| author | Cahyawijaya, Samuel Lovenia, Holy Koto, Fajri Putri, Rifki Afina Dave, Emmanuel Lee, Jhonson Shadieq, Nuur Cenggoro, Wawan Akbar, Salsabil Maulana Mahendra, Muhammad Ihza Putri, Dea Annisayanti Wilie, Bryan Winata, Genta Indra Aji, Alham Fikri Purwarianti, Ayu Fung, Pascale |
| author_facet | Cahyawijaya, Samuel Lovenia, Holy Koto, Fajri Putri, Rifki Afina Dave, Emmanuel Lee, Jhonson Shadieq, Nuur Cenggoro, Wawan Akbar, Salsabil Maulana Mahendra, Muhammad Ihza Putri, Dea Annisayanti Wilie, Bryan Winata, Genta Indra Aji, Alham Fikri Purwarianti, Ayu Fung, Pascale |
| contents | Large language models (LLMs) show remarkable human-like capability in various domains and languages. However, a notable quality gap arises in low-resource languages, e.g., Indonesian indigenous languages, rendering them ineffective and inefficient in such linguistic contexts. To bridge this quality gap, we introduce Cendol, a collection of Indonesian LLMs encompassing both decoder-only and encoder-decoder architectures across a range of model sizes. We highlight Cendol's effectiveness across a diverse array of tasks, attaining 20% improvement, and demonstrate its capability to generalize to unseen tasks and indigenous languages of Indonesia. Furthermore, Cendol models showcase improved human favorability despite their limitations in capturing indigenous knowledge and cultural values in Indonesia. In addition, we discuss the shortcomings of parameter-efficient tunings, such as LoRA, for language adaptation. Alternatively, we propose the usage of vocabulary adaptation to enhance efficiency. Lastly, we evaluate the safety of Cendol and showcase that safety in pre-training in one language such as English is transferable to low-resource languages, such as Indonesian, even without RLHF and safety fine-tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06138 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages Cahyawijaya, Samuel Lovenia, Holy Koto, Fajri Putri, Rifki Afina Dave, Emmanuel Lee, Jhonson Shadieq, Nuur Cenggoro, Wawan Akbar, Salsabil Maulana Mahendra, Muhammad Ihza Putri, Dea Annisayanti Wilie, Bryan Winata, Genta Indra Aji, Alham Fikri Purwarianti, Ayu Fung, Pascale Computation and Language Large language models (LLMs) show remarkable human-like capability in various domains and languages. However, a notable quality gap arises in low-resource languages, e.g., Indonesian indigenous languages, rendering them ineffective and inefficient in such linguistic contexts. To bridge this quality gap, we introduce Cendol, a collection of Indonesian LLMs encompassing both decoder-only and encoder-decoder architectures across a range of model sizes. We highlight Cendol's effectiveness across a diverse array of tasks, attaining 20% improvement, and demonstrate its capability to generalize to unseen tasks and indigenous languages of Indonesia. Furthermore, Cendol models showcase improved human favorability despite their limitations in capturing indigenous knowledge and cultural values in Indonesia. In addition, we discuss the shortcomings of parameter-efficient tunings, such as LoRA, for language adaptation. Alternatively, we propose the usage of vocabulary adaptation to enhance efficiency. Lastly, we evaluate the safety of Cendol and showcase that safety in pre-training in one language such as English is transferable to low-resource languages, such as Indonesian, even without RLHF and safety fine-tuning. |
| title | Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.06138 |