Ultra-Low-Dimensional Prompt Tuning via Random Projection

[2502.04501] Ultra-Low-Dimensional Prompt Tuning via Random Projection Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2502.04501 (cs) [Submitted on 6 Feb 2025 ( v1 ), last revised 12 Apr 2026 (this version, v3)] Title: Ultra-Low-Dimensional Prompt Tuning via Random Projection Authors: Zijun Wu , Yongchang Hao , Lili Mou View a PDF of the paper titled Ultra-Low-Dimensional Prompt Tuning via Random Projection, by Zijun Wu and 2 other authors View PDF HTML (experimental) Abstract: Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tuning method that addresses parameter-efficiency by learning prompt embeddings, but these embeddings are typically tied to the model's hidden dimensionality, limiting parameter saving. In this paper, we propose Ultra-Low-dimensional Prompt Tuning (ULPT), a simple yet effective method that optimizes prompts in a low-dimensional space (e.g., 2D) and uses a frozen random matrix for up-projection. ULPT can achieve 98% reduction in the training parameters compared to vanilla prompt tuning while preserving performance. Our extensive experiments across over 20 NLP tasks demonstrate that ULPT consistently outperforms recent parameter-efficient tuning methods using significantly fewer parameters, making it well-suited as a storage-efficient framework for massive LLM customization. Comments: Accepted by EACL 2026 (Main Conference, Long Paper) Subjects: Computation and Language (cs.CL) Cite as: arXiv:2502.04501 [cs.CL] (or arXiv:2502.04501v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2502.04501 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zijun Wu [ view email ] [v1] Thu, 6 Feb 2025 21:00:29 UTC (246 KB) [v2] Mon, 26 Jan 2026 22:29:09 UTC (273 KB) [v3] Sun, 12 Apr 2026 01:21:55 UTC (275 KB) Full-text links: Access Paper: View a PDF of the paper titled Ultra-Low-Dimensional Prompt Tuning via Random Projection, by Zijun Wu and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2025-02 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Decibel Telematic Performances#368778
• Backscatter Communication Through Disordered Media Enabled by a Programmable Leaky Cavity#226789
• CaSty - Calibrating Stylized Items, version 2.4#208070
• Codebook-Based Effective CSI Feedback for Precoding Design in MIMO Systems#1064049
• On Scalable Pseudorandom Unitaries and the Unitary Synthesis Problem#175146