arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.14522cs.CLcs.LG
收藏

面向多模型间的统一任务嵌入:弥合基于提示的大语言模型及其他模型间的差距

Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond

University of Warwick(华威大学);The Alan Turing Institute(阿兰·图灵研究所)

Xinyu Wang, Hainiu Xu, Lin Gui, Yulan He

AI总结:

针对现有任务嵌入方法难以适配无梯度提示引导型LLMs、跨模型适应性差的问题,提出统一任务嵌入框架FUTE,将多类模型的任务嵌入映射到同一向量空间,实现跨模型相似性分析,拓展了任务嵌入的应用场景且性能不逊于架构特定方法。

摘要:

任务嵌入是一种捕捉任务特定信息的元学习技术,已在多任务学习、模型编辑和可解释性等领域得到广泛应用。然而,随着以无梯度方式运行的提示引导型大语言模型(LLMs)的出现,任务嵌入面临着挑战。现有的任务嵌入方法依赖于经过微调的任务特定语言模型,这阻碍了任务嵌入在不同模型(尤其是基于提示的LLMs)间的适应性。为了在LLM时代发挥任务嵌入的潜力,我们提出了统一任务嵌入框架(FUTE),将来自各类模型(包括较小的语言模型和采用不同提示的LLMs)的任务嵌入协调到单个向量空间中。这种统一性使得不同模型间的相似性比较与分析成为可能,拓宽了现有任务嵌入方法在多模型场景下的适用范围与效用,同时保持其性能与架构特定方法相当。

英文摘要:

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence of prompt-guided Large Language Models (LLMs) operating in a gradient-free manner. Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders the adaptability of task embeddings across diverse models, especially prompt-based LLMs. To hardness the potential of task embeddings in the era of LLMs, we propose a framework for unified task embeddings (FUTE), harmonizing task embeddings from various models, including smaller language models and LLMs with varied prompts, within a single vector space. Such uniformity enables comparison and analysis of similarities amongst different models, broadening the scope and utility of existing task embedding methods in multi-model scenarios, while maintaining their performance comparable to architecture-specific 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。

↑