SuperPos-Prompt: Enhancing Soft Prompt Tuning of Language Models with Superposition of Multi Token Embeddings
Soft prompt tuning techniques have recently gained traction as an effective strategy for the parameter-efficient tuning of pretrained language models, particularly minimizing the required adjustment of model parameters. Despite their growing use, achieving optimal tuning with soft prompts, especially for smaller datasets, remains a substantial challenge. This study makes two contributions in this domain: (i) we introduce SuperPos-Prompt, a new reparameterization technique employing the superposition of multiple pretrained vocabulary embeddings to improve the learning of soft prompts. Our experiments across several GLUE and SuperGLUE benchmarks consistently highlight SuperPos-Prompt's superiority over Residual Prompt tuning, exhibiting an average score increase of $+6.4$ in T5-Small and $+5.0$ in T5-Base along with a faster convergence. Remarkably, SuperPos-Prompt occasionally outperforms even full fine-tuning methods. (ii) Additionally, we demonstrate enhanced performance and rapid convergence by omitting dropouts from the frozen network, yielding consistent improvements across various scenarios and tuning methods.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt
Enhancing the zero-shot performance of instruction-following models requires heavy computation, either by scaling the total number of training datasets or the model size. In this work, we explore how retrieval of soft pr…
Instruction FollowingRetrievalGenerating Synthetic Datasets for Few-shot Prompt Tuning
A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, limiting its scope of application. In this…
Few-Shot LearningMRPCQQPSentence+2Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
Despite the successes of large language models (LLMs), they exhibit significant drawbacks, particularly when processing long contexts. Their inference cost scales quadratically with respect to sequence length, making it …
Question AnsweringRAGRetrievalRetrieval-augmented GenerationSoft Language Prompts for Language Transfer
Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications thr…
Cross-Lingual Transferparameter-efficient fine-tuningTransfer LearningInfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of the prompts. We also empirically observ…
Language ModelingLanguage ModellingNatural Language Understanding