基于Logit可分性驱动的样本与多类相关词选择以推进上下文学习
Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning
AI总结:
本文提出LICL方法,通过logit可分性优化样本与标签选择,并整合多个类相关词,显著提升ICL在分类任务中的性能。
摘要:
上下文学习(ICL)示例的有效组织是提升大型语言模型(LLM)响应质量的关键。为创建更好的样本-标签对以指导LLM理解,我们引入了logit separability(logit可分性),这是一种在logit层面评估样本和类相关词清晰度的标准。这促进了样本和标签选择的优化,增强了ICL示例中提供的信息的精确度。此外,我们发现为每个样本纳入多个类相关词,而非依赖单一类名,通过提供更广泛的标签信息来提升性能。基于这些见解,我们提出LICL,一种基于logit separability的方法,联合组织样本并将多个类相关词整合到每个样本-标签对中。在七个分类数据集上的评估表明,该方法通过提供更清晰的指令和更丰富的标签信息,显著提升了ICL性能。
英文摘要:
Effective organization of in-context learning (ICL) demonstrations is key to improving the quality of large language model (LLM) responses. To create better sample-label pairs that instruct LLM understanding, we introduce logit separability, a criterion to assess the clarity of both samples and class-related words at the logit level. This facilitates the optimization of sample and label selection, enhancing the precision of information provided in ICL demonstrations. Additionally, we find that incorporating multiple class-related words for each sample, rather than relying on a single class name, improves performance by offering a broader range of label information. Building on these insights, we propose LICL, a logit separability-based method that jointly organizes samples and integrates multiple class-related words into each sample-label pair. Evaluations across seven classification datasets show that this approach significantly improves ICL performance by providing clearer instructions and richer label information.
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。