Abstract:Prompt tuning is an efficient solution for training large language models (LLMs). However, current soft-prompt-based methods often sacrifice multi-task modularity, requiring the training process to be fully or partially repeated for each newly added task. While recent work on task vectors applied arithmetic operations on full model weights to achieve the desired multi-task performance, a similar approach for soft-prompts is still missing. To this end, we introduce Task Prompt Vectors, created by element-wise difference between weights of tuned soft-prompts and their random initialization. Experimental results on 12 NLU datasets show that task prompt vectors can be used in low-resource settings to effectively initialize prompt tuning on similar tasks. In addition, we show that task prompt vectors are independent of the random initialization of prompt tuning on 2 different language model architectures. This allows prompt arithmetics with the pre-trained vectors from different tasks. In this way, we provide a competitive alternative to state-of-the-art baselines by arithmetic addition of task prompt vectors from multiple tasks.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2408.01119 [cs.CL] |
| (or arXiv:2408.01119v4 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2408.01119 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1007/978-3-662-72243-5_5
DOI(s) linking to related resources |
Submission history
From: Robert Belanec [view email]
[v1]
Fri, 2 Aug 2024 09:00:03 UTC (3,406 KB)
[v2]
Wed, 23 Oct 2024 14:37:50 UTC (3,410 KB)
[v3]
Thu, 3 Jul 2025 09:32:20 UTC (1,439 KB)
[v4]
Tue, 12 May 2026 18:55:05 UTC (1,439 KB)