待翻译：SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters

AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。

--> [Submitted on 26 May 2026] Title:SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters View a PDF of the paper titled SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters, by Josh McGiff and 3 other authors View PDF HTML (experimental) Abstract:Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved practical challenge. We present SemiAdapt-Instruct, a modular framework that discovers latent instruction domains, trains per-domain LoRA adapters in parallel, and performs parameter-free routing, incorporating new domains via single-adapter training without modifying existing components. SemiAdapt-Instruct outperforms full model fine-tuning across all configurations on both ROUGE-L and LLM-as-a-judge evaluation, while matching single LoRA fine-tuning and delivering extensibility that monolithic approaches cannot provide. We empirically demonstrate this extensibility by showing that updating a single adapter with new domain data outperforms all monolithic baselines. Our study also finds that independent discovery methods converge on the same specialisation-friendly domains. These findings demonstrate that decomposing heterogeneous instruction data into latent domains enables extensible NLP systems where evolving domains require only targeted single-adapter updates, eliminating the need for full model retraining. Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2608.05161 [cs.CL] (or arXiv:2608.05161v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.05161 arXiv-issued DOI via DataCite Submission history From: Josh McGiff Mr [view email] [v1] Tue, 26 May 2026 07:01:35 UTC (590 KB) Full-text links: Access Paper: View a PDF of the paper titled SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters, by Josh McGiff and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-08 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: 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?)