paper-with-me

Papers

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

2023-06-08 · NeurIPS 2023 11

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 observe that conventional prompt tuning methods cannot encode and learn sufficient task-relevant information from prompt tokens. In this work, we develop an information-theoretic framework that formulates soft prompt tuning as maximizing mutual information between prompts and other model parameters (or encoded representations). This novel view helps us to develop a more efficient, accurate and robust soft prompt tuning method InfoPrompt. With this framework, we develop two novel mutual information based loss functions, to (i) discover proper prompt initialization for the downstream tasks and learn sufficient task-relevant information from prompt tokens and (ii) encourage the output representation from the pretrained language model to be more aware of the task-relevant information captured in the learnt prompt. Extensive experiments validate that InfoPrompt can significantly accelerate the convergence of the prompt tuning and outperform traditional prompt tuning methods. Finally, we provide a formal theoretical result for showing to show that gradient descent type algorithm can be used to train our mutual information loss.

📄 PDF Abstract BibTeX arXiv:2306.04933

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingNatural Language Understanding

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

On the Role of Attention in Prompt-tuning

2023-06-06 · Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis

Prompt-tuning is an emerging strategy to adapt large language models (LLM) to downstream tasks by learning a (soft-)prompt parameter from data. Despite its success in LLMs, there is limited theoretical understanding of t…

When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations

2023-10-30 · Aleksandar Petrov, Philip H. S. Torr, Adel Bibi

Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of …

In-Context Learning

Dynamic Prompting: A Unified Framework for Prompt Tuning

2023-03-06 · Xianjun Yang, Wei Cheng, Xujiang Zhao, Wenchao Yu 외

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language models (PLMs), vision pretrained models, …

Position

Alternating Training-based Label Smoothing Enhances Prompt Generalization

2025-08-25 · Yang Chen, Yanbin Wei, Ke Jin, Yi Kong 외 arxiv

Recent advances in pre-trained vision-language models have demonstrated remarkable zero-shot generalization capabilities. To further enhance these models' adaptability to various downstream tasks, prompt tuning has emerg…

parameter-efficient fine-tuningZero-shot Generalization

Optimizing Soft Prompt Tuning via Structural Evolution

2026-02-18 · Zhenzhen Huang, Chaoning Zhang, Haoyu Bian, Songbo Zhang 외 arxiv

Soft prompt tuning leverages continuous embeddings to capture task-specific information in large pre-trained language models (LLMs), achieving competitive performance in few-shot settings. However, soft prompts rely on h…