Sign up to save your podcasts
Or
Share Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
🤗 Upvotes: 25 | cs.CL
Authors:
Ananth Muppidi, Abhilash Nandy, Sambaran Bandyopadhyay
Title:
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
Arxiv:
http://arxiv.org/abs/2506.05629v1
Abstract:
The performance of large language models in domain-specific tasks necessitates fine-tuning, which is computationally expensive and technically challenging. This paper focuses on parameter-efficient fine-tuning using soft prompting, a promising approach that adapts pre-trained models to downstream tasks by learning a small set of parameters. We propose a novel Input Dependent Soft Prompting technique with a self-Attention Mechanism (ID-SPAM) that generates soft prompts based on the input tokens and attends different tokens with varying importance. Our method is simple and efficient, keeping the number of trainable parameters small. We show the merits of the proposed approach compared to state-of-the-art techniques on various tasks and show the improved zero shot domain transfer capability.
View all episodes
By Jingwen Liang, Gengyu Wang🤗 Upvotes: 25 | cs.CL
Authors:
Ananth Muppidi, Abhilash Nandy, Sambaran Bandyopadhyay
Title:
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
Arxiv:
http://arxiv.org/abs/2506.05629v1
Abstract:
The performance of large language models in domain-specific tasks necessitates fine-tuning, which is computationally expensive and technically challenging. This paper focuses on parameter-efficient fine-tuning using soft prompting, a promising approach that adapts pre-trained models to downstream tasks by learning a small set of parameters. We propose a novel Input Dependent Soft Prompting technique with a self-Attention Mechanism (ID-SPAM) that generates soft prompts based on the input tokens and attends different tokens with varying importance. Our method is simple and efficient, keeping the number of trainable parameters small. We show the merits of the proposed approach compared to state-of-the-art techniques on various tasks and show the improved zero shot domain transfer capability.