The NLP community recently saw the release of a new large open-access
multilingual language model, BLOOM (BigScience et al., 2022) covering 46
languages. We focus on BLOOM's multilingual ability by evaluating its machine
translation performance across several datasets (WMT, Flores-101 and DiaBLa)
and language pairs (high- and low-resourced). Our results show that 0-shot
performance suffers from overgeneration and generating in the wrong language,
but this is greatly improved in the few-shot setting, with very good results
for a number of language pairs. We study several aspects including prompt
design, model sizes, cross-lingual transfer and the use of discursive context.

本文评估了覆盖 46 种语言的新型开放访问的大型多语种语言模型 BLOOM 在机器翻译上的表现，结果显示少量样本学习模式下，该模型在许多语言对中表现良好，但 0-shot 性能受到过度生成和错误语言生成的影响。

研究大型多语言语言模型的翻译性能：以 BLOOM 为例

Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM

We view the landscape of large language models (LLMs) through the lens of the
recently released BLOOM model to understand the performance of BLOOM and other
decoder-only LLMs compared to BERT-style encoder-only models. We achieve this
by evaluating the smaller BLOOM model variants (\textit{350m/560m} and
\textit{1b3/1b7}) on several NLP benchmark datasets and popular leaderboards.
We make the following observations: (1) BLOOM performance does not scale with
parameter size, unlike other LLMs like GPT and BERT. Experiments fine-tuning
BLOOM models show that the 560m variant performs similarly to or better than
the 1b7 variant, (2) Zero-shot cross-lingual and multi-lingual fine-tuning
experiments show that BLOOM is at par or worse than monolingual GPT-2 models,
and (3) Toxicity analysis of prompt-based text generation using the
RealToxicityPrompts dataset shows that the text generated by BLOOM is at least
17\% less toxic than GPT-2 and GPT-3 models.

通过评估较小的 BLOOM 模型变体（350m / 560m 和 1b3 / 1b7），我们发现：（1）与 GPT 和 BERT 等 LLM 不同，BLOOM 表现不随参数大小变化；（2）跨语言和多语言微调实验证明 BLOOM 与单语 GPT-2 模型相当或更差；（3）使用 RealToxicityPrompts 数据集的提示文本生成的毒性分析表明，BLOOM 生成的文本至少比 GPT-2 和 GPT-3 模型不良反应低 17％。

理解 BLOOM：多元自然语言处理任务的实证研究

Understanding BLOOM: An empirical study on diverse NLP tasks

Large language models (LLMs) have been shown to be able to perform new tasks
based on a few demonstrations or natural language instructions. While these
capabilities have led to widespread adoption, most LLMs are developed by
resource-rich organizations and are frequently kept from the public. As a step
towards democratizing this powerful technology, we present BLOOM, a
176B-parameter open-access language model designed and built thanks to a
collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer
language model that was trained on the ROOTS corpus, a dataset comprising
hundreds of sources in 46 natural and 13 programming languages (59 in total).
We find that BLOOM achieves competitive performance on a wide variety of
benchmarks, with stronger results after undergoing multitask prompted
finetuning. To facilitate future research and applications using LLMs, we
publicly release our models and code under the Responsible AI License.

BLOOM 是一个 176B 参数的解码器 - 只有 Transformer 语言模型，它使用 ROOTS 语料库进行训练，并在多任务提示微调后达到了竞争力强的结果。该研究呼吁公开此类研究并在负责任的 AI 许可下发布其模型和代码，以便未来的研究和应用。