探索提示调优中嵌入先验以提升可解释性和可控性
Exploring Embedding Priors in Prompt-Tuning for Improved Interpretability and Control
AI总结：
本文研究了提示调优中嵌入坍缩现象对模型性能的影响，提出嵌入先验以提升可解释性和可控性，并发现不同激活区域的嵌入能有效提升任务表现。
摘要：
提示调优是一种通过修改提示嵌入来适应新任务的高效方法，其计算开销极低。在本工作中，我们研究了在提示调优中经常观察到的嵌入坍缩现象对最终模型性能的重要性。为了解决这个问题，我们设计了嵌入先验，并将其与收敛的软提示调优和深度提示调优的后验进行了比较。我们的发现表明，先验强烈地影响了调优嵌入的位置，模型可以有效地使用来自激活空间不同部分的嵌入，包括完全新的区域。由于最终的提示调优能力有限，我们假设可控的提示调优后验可能成为诸如链式思维（COT）蒸馏等任务的良好起点。我们的实验还显示，生成的轨迹并不局限于模型的激活空间。然而，对于遥远的任务（例如NLP和算术），激活存在明显的聚类，而NLP任务（例如问答和MLM）之间的激活则位于同一聚类中。这些观察结果引发了关于单个激活聚类对大语言模型泛化能力重要性的问题。
英文摘要：
Prompt-Tuning is an efficient method for adapting pre-trained language models to new tasks with minimal computational overhead by modifying prompt embeddings. In this work, we investigate how crucial the phenomenon of embedding collapse, frequently observed in Prompt-Tuning, is for the final performance of the model. To address this question, we designed embedding priors and compared them with posteriors of the converged Soft and Deep Prompt-Tuning methods. Our findings suggest that priors strongly affect the position of the tuned embeddings, and models can effectively work with embeddings from different parts of activation spaces, including completely new regions. As the final Prompt-Tuning capabilities are limited, we hypothesize that controllable Prompt-Tuning posteriors may serve as a good starting point for tasks such as chain-of-thought (COT) distillation. Our experiments also show that generated trajectories are not localized in the activation space of the models. However, there are distinct clusters of activations for distant tasks (e.g., NLP and arithmetic), while activations between NLP tasks (e.g., Question-Answering and MLM) lie in the same cluster. These observations raise questions about the importance of a single activation cluster for the generalization abilities of large language models.
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。
