Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911853349699584 |
|---|---|
| author | Zhan, Runzhe Yang, Xinyi Wong, Derek F. Chao, Lidia S. Zhang, Yue |
| author_facet | Zhan, Runzhe Yang, Xinyi Wong, Derek F. Chao, Lidia S. Zhang, Yue |
| contents | While supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences, concerns have been raised about the depth of this alignment, with some critiques suggesting it is merely "superficial". We critically examine this hypothesis within the scope of cross-lingual generation tasks, proposing that the effectiveness of SFT may be constrained by its reliance on prior tokens to guide cross-lingual generation. Based on this crucial insight, and in response to the challenges posed by the costly and limited availability of non-English data for SFT, we introduce a novel training-free alignment method named PreTTY, which employs minimal task-related prior tokens to bridge the foundation LLM and the SFT LLM, achieving comparable performance without training. Experiments on machine translation and part-of-speech tagging across eight languages demonstrate the efficacy of PreTTY in cross-lingual settings. Remarkably, by initiating the decoding process with only one or two prior tokens, foundation LLMs can achieve performance comparable to their SFT counterparts. This method presents a cost-effective alternative to SFT and advances the democratization of multilingual LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16766 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model Zhan, Runzhe Yang, Xinyi Wong, Derek F. Chao, Lidia S. Zhang, Yue Computation and Language Artificial Intelligence While supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences, concerns have been raised about the depth of this alignment, with some critiques suggesting it is merely "superficial". We critically examine this hypothesis within the scope of cross-lingual generation tasks, proposing that the effectiveness of SFT may be constrained by its reliance on prior tokens to guide cross-lingual generation. Based on this crucial insight, and in response to the challenges posed by the costly and limited availability of non-English data for SFT, we introduce a novel training-free alignment method named PreTTY, which employs minimal task-related prior tokens to bridge the foundation LLM and the SFT LLM, achieving comparable performance without training. Experiments on machine translation and part-of-speech tagging across eight languages demonstrate the efficacy of PreTTY in cross-lingual settings. Remarkably, by initiating the decoding process with only one or two prior tokens, foundation LLMs can achieve performance comparable to their SFT counterparts. This method presents a cost-effective alternative to SFT and advances the democratization of multilingual LLMs. |
| title | Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2404.16766 |