Anti-LM Decoding for Zero-shot In-context Machine Translation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909158666665984 |
|---|---|
| author | Sia, Suzanna DeLucia, Alexandra Duh, Kevin |
| author_facet | Sia, Suzanna DeLucia, Alexandra Duh, Kevin |
| contents | Zero-shot In-context learning is the phenomenon where models can perform the task simply given the instructions. However, pre-trained large language models are known to be poorly calibrated for this task. One of the most effective approaches to handling this bias is to adopt a contrastive decoding objective, which accounts for the prior probability of generating the next token by conditioning on some context. This work introduces an Anti-Language Model objective with a decay factor designed to address the weaknesses of In-context Machine Translation. We conduct our experiments across 3 model types and sizes, 3 language directions, and for both greedy decoding and beam search ($B=5$). The proposed method outperforms other state-of-art decoding objectives, with up to $20$ BLEU point improvement from the default objective observed in some settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_08324 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Anti-LM Decoding for Zero-shot In-context Machine Translation Sia, Suzanna DeLucia, Alexandra Duh, Kevin Computation and Language Artificial Intelligence Zero-shot In-context learning is the phenomenon where models can perform the task simply given the instructions. However, pre-trained large language models are known to be poorly calibrated for this task. One of the most effective approaches to handling this bias is to adopt a contrastive decoding objective, which accounts for the prior probability of generating the next token by conditioning on some context. This work introduces an Anti-Language Model objective with a decay factor designed to address the weaknesses of In-context Machine Translation. We conduct our experiments across 3 model types and sizes, 3 language directions, and for both greedy decoding and beam search ($B=5$). The proposed method outperforms other state-of-art decoding objectives, with up to $20$ BLEU point improvement from the default objective observed in some settings. |
| title | Anti-LM Decoding for Zero-shot In-context Machine Translation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2311.08324 |