View in EDS

Semantic spherical mixup: geometry-aware data augmentation in latent manifolds for parameter-efficient language model adaptation.

Saved in:
Bibliographic Details
Title: Semantic spherical mixup: geometry-aware data augmentation in latent manifolds for parameter-efficient language model adaptation.
Authors: Singh, Pradeep1 (AUTHOR) pradeep.cs@sric.iitr.ac.in, Raman, Balasubramanian1 (AUTHOR) bala@cs.iitr.ac.in
Source: Knowledge & Information Systems. 3/17/2026, Vol. 68 Issue 1, p1-23. 23p.
Subjects: Data augmentation, Interpolation, Submanifolds, Sentiment analysis
Abstract: Task-specific fine-tuning has become the de facto method for adapting large language models (LLMs) to downstream objectives, but it adds considerable computational and storage overhead and can destabilise optimisation. We introduce Semantic Mixup via Spherical Interpolation (SMSI), a geometry-aware data augmentation scheme that operates entirely in the latent space of a frozen encoder. SMSI first normalises the encoder outputs, thereby constraining them to lie on the unit hypersphere, and then views each label region as a locally spherical submanifold on which we synthesise new samples by Slerp-interpolating between cluster-level neighbours that share the same label. Experiments on seven emotion- and sentiment-analysis benchmarks show that SMSI achieves competitive performance while using roughly 10 × fewer trainable parameters than full fine-tuning and matching the accuracy of parameter-efficient approaches such as LoRA. These findings demonstrate that latent space semantic interpolation can offer a lightweight alternative to task-specific adaptation. [ABSTRACT FROM AUTHOR]
Copyright of Knowledge & Information Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Task-specific fine-tuning has become the de facto method for adapting large language models (LLMs) to downstream objectives, but it adds considerable computational and storage overhead and can destabilise optimisation. We introduce Semantic Mixup via Spherical Interpolation (SMSI), a geometry-aware data augmentation scheme that operates entirely in the latent space of a frozen encoder. SMSI first normalises the encoder outputs, thereby constraining them to lie on the unit hypersphere, and then views each label region as a locally spherical submanifold on which we synthesise new samples by Slerp-interpolating between cluster-level neighbours that share the same label. Experiments on seven emotion- and sentiment-analysis benchmarks show that SMSI achieves competitive performance while using roughly 10 × fewer trainable parameters than full fine-tuning and matching the accuracy of parameter-efficient approaches such as LoRA. These findings demonstrate that latent space semantic interpolation can offer a lightweight alternative to task-specific adaptation. [ABSTRACT FROM AUTHOR]
ISSN:02191377
DOI:10.1007/s10115-026-02719-z