GRASP LoRA: GRPO指导的适配器稀疏性策略用于跨语言迁移
GRASP LoRA: GRPO Guided Adapter Sparsity Policy for Cross Lingual Transfer
AI总结：
GRASP LoRA通过GRPO指导的适配器稀疏性策略提升跨语言迁移的性能，减少计算成本并提高资源利用效率。
摘要：
参数高效的微调是一种在计算资源或数据有限时将大语言模型适应到新语言的方法，但适配器管道通常通过网格搜索选择全局剪枝比率。这种做法计算成本高且依赖开发集，因为它重复训练、冻结稀疏性并错过分数最优解。我们引入了GRASP LoRA（GRPO指导的适配器稀疏性策略），将全局稀疏性视为一个可学习的控制变量。一个GRPO控制器在训练过程中交替进行，定期在小的微型开发集上探测候选剪枝比率，并从其奖励信号更新一个单一的全局剪枝比率。它在冻结的骨干网络上操作合并的源和目标LoRA适配器，并用一个控制器运行学习剪枝比率，随后进行一次最终的合并和剪枝微调运行，将剪枝固定为该比率。在从英语到阿拉伯语和中文的跨语言迁移中，包括XL-Sum摘要和MLQA提取性问答（使用Llama 3 8B），GRASP LoRA在语义忠实性、内容覆盖和答案质量上优于强目标仅和合并剪枝基线。它将端到端运行时间相对于网格搜索减少了多倍，降低了对大规模开发集的依赖，并使适配器重用在低资源部署中成为可能。
英文摘要：
Parameter efficient fine tuning is a way to adapt LLMs to new languages when compute or data are limited, yet adapter pipelines usually choose a global prune ratio by grid search. This practice is computationally expensive and development set intensive, since it repeats training, freezes sparsity, and misses fractional optima. We introduce GRASP LoRA (GRPO Guided Adapter Sparsity Policy), which treats global sparsity as a learnable control variable. A GRPO controller interleaves with training, periodically probing candidate prune ratios on a small micro development set and updating a single global prune ratio online from its reward signal. It operates on merged source and target LoRA adapters on a frozen backbone and replaces grid search with one controller run that learns a prune ratio, followed by a single final merge and prune fine tuning run with pruning fixed to that ratio. On cross lingual transfer from English into Arabic and Chinese, including XL-Sum summarization and MLQA extractive question answering with Llama 3 8B, GRASP LoRA improves semantic faithfulness, content coverage, and answer quality over strong target only and merge and prune baselines. It reduces end to end runtime by multiple times relative to grid search, lowers reliance on large development sets, and makes adapter reuse practical for low resource deployment.
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。
