Yang Liu, Dilek Hakkani-Tur, Yifan Chen, Di Jin, Devamanyu Hazarika, Mahdi Namazifar
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM), prefix-tuning can obtain strong performance by training only a small portion of parameters. In this paper, we propose to understand and further develop prefix-tuning through the kernel lens. Specifically, we make an analogy between prefixes and inducing variables in kernel methods and hypothesize that prefixes serving as inducing variables would improve their overall mechanism. From the kernel estimator perspective, we suggest a new variant of prefix-tuning-inducer-tuning, which shares the exact mechanism as prefix-tuning while leveraging the residual form found in adaptertuning. This mitigates the initialization issue in prefix-tuning. Through comprehensive empirical experiments on natural language understanding and generation tasks, we demonstrate that inducer-tuning can close the performance gap between prefix-tuning and fine-tuning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.14469")
get_code_for_paper("2210.14469")
have("2210.14469")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2210.14469.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2210.14469)
Connect an agent — have() is free.