arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.18583cs.CL
收藏

命中最佳点!大语言模型的 Span 级集成

Hit the Sweet Spot! Span-Level Ensemble for Large Language Models

School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Wuhan AI Research(武汉人工智能研究院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

Yangyifan Xu, Jianghao Chen, Junhong Wu, Jiajun Zhang

AI总结:

针对LLM样本级和token级集成的不足,提出span级集成方法SweetSpan,通过候选span生成与基于困惑度的相互评估实现稳健选择,在标准与挑战性设置下均展现出有效性与稳健性。

摘要:

集成各种 LLM 以释放其互补潜力并利用其各自优势具有很高的价值。以往的研究通常集中在两个主要范式上:样本级集成和 token 级集成。样本级集成方法要么选择要么混合完全生成的输出,这阻碍了在生成过程中对输出进行动态纠正和增强。另一方面,token 级集成方法通过在每个生成步骤进行细粒度集成来实现实时纠正。然而,单个 token 携带的信息相当有限,导致每一步的决策并非最优。为了解决这些问题,我们提出了 SweetSpan,一种 span 级集成方法,它有效地平衡了对实时调整的需求和准确集成决策所需的信息。我们的方法包含两个关键步骤:首先,我们让每个候选模型基于共享前缀独立生成候选 span。其次,我们计算困惑度分数以促进候选模型之间的相互评估,并通过过滤不忠实的分数来实现稳健的 span 选择。为了全面评估集成方法,除了标准设置(集成表现最佳的模型)外,我们还提出了一种新的挑战性设置(集成存在显著性能差距的模型),以在更现实的场景中评估模型集成的性能。在标准设置和挑战性设置下,跨各种语言生成任务的实验结果证明了,与以往的集成方法相比,我们方法的有效性、稳健性和通用性。

英文摘要:

Ensembling various LLMs to unlock their complementary potential and leverage their individual strengths is highly valuable. Previous studies typically focus on two main paradigms: sample-level and token-level ensembles. Sample-level ensemble methods either select or blend fully generated outputs, which hinders dynamic correction and enhancement of outputs during the generation process. On the other hand, token-level ensemble methods enable real-time correction through fine-grained ensemble at each generation step. However, the information carried by an individual token is quite limited, leading to suboptimal decisions at each step. To address these issues, we propose SweetSpan, a span-level ensemble method that effectively balances the need for real-time adjustments and the information required for accurate ensemble decisions. Our approach involves two key steps: First, we have each candidate model independently generate candidate spans based on the shared prefix. Second, we calculate perplexity scores to facilitate mutual evaluation among the candidate models and achieve robust span selection by filtering out unfaithful scores. To comprehensively evaluate ensemble methods, we propose a new challenging setting (ensemble models with significant performance gaps) in addition to the standard setting (ensemble the best-performing models) to assess the performance of model ensembles in more realistic scenarios. Experimental results in both standard and challenging settings across various language generation tasks demonstrate the effectiveness, robustness, and versatility of our approach compared with previous ensemble methods.

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。

↑