BayLing：通过交互式翻译弥合大语言模型的跨语言对齐与指令跟随
BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
AI总结：
BayLing通过交互式翻译任务将英语的语言生成和指令跟随能力迁移至其他语言，基于LLaMA构建的130亿参数模型，性能接近GPT-3.5-turbo，并发布了测试集BayLing-80。
摘要：
大语言模型（LLMs）在语言理解和生成方面展现出了卓越的能力。从基础LLM推进到指令跟随LLM，指令微调在使LLM与人类偏好对齐方面发挥着至关重要的作用。然而，现有的LLM通常专注于英语，导致在非英语语言上表现不佳。为了提高非英语语言的性能，有必要为基础LLM收集特定于语言的训练数据，并为指令微调构建特定于语言的指令，这两者都是繁重的负担。为了最小化人类工作量，我们提出通过交互式翻译任务将语言生成和指令跟随的能力从英语迁移到其他语言。我们开发了BayLing，一个指令跟随LLM，利用LLaMA作为基础LLM，并自动构建交互式翻译指令用于微调。广泛的评估表明，尽管BayLing仅使用了130亿参数的较小规模，但其性能可与GPT-3.5-turbo相媲美。在翻译任务上的实验结果显示，在自动评估下，BayLing的单轮翻译能力达到GPT-4的95%，在人工评估下，其交互式翻译能力达到GPT-3.5-turbo的96%。为了评估在一般任务上的性能，我们创建了一个多轮指令测试集，称为BayLing-80。在BayLing-80上的实验结果表明，BayLing达到了GPT-3.5-turbo性能的89%。BayLing在中文高考和英语SAT的知识评估中也表现出色，在众多指令跟随LLM中仅次于GPT-3.5-turbo。BayLing的演示、主页、代码和模型均已公开。
英文摘要：
Large language models (LLMs) have demonstrated remarkable prowess in language understanding and generation. Advancing from foundation LLMs to instructionfollowing LLMs, instruction tuning plays a vital role in aligning LLMs to human preferences. However, the existing LLMs are usually focused on English, leading to inferior performance in non-English languages. In order to improve the performance for non-English languages, it is necessary to collect language-specific training data for foundation LLMs and construct language-specific instructions for instruction tuning, both of which are heavy loads. To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task. We have developed BayLing, an instruction-following LLM by utilizing LLaMA as the foundation LLM and automatically constructing interactive translation instructions for instructing tuning. Extensive assessments demonstrate that BayLing achieves comparable performance to GPT-3.5-turbo, despite utilizing a considerably smaller parameter size of only 13 billion. Experimental results on translation tasks show that BayLing achieves 95% of single-turn translation capability compared to GPT-4 with automatic evaluation and 96% of interactive translation capability compared to GPT-3.5-turbo with human evaluation. To estimate the performance on general tasks, we created a multi-turn instruction test set called BayLing-80. The experimental results on BayLing-80 indicate that BayLing achieves 89% of performance compared to GPT-3.5-turbo. BayLing also demonstrates outstanding performance on knowledge assessment of Chinese GaoKao and English SAT, second only to GPT-3.5-turbo among a multitude of instruction-following LLMs. Demo, homepage, code and models of BayLing are available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
